© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111320
    Prev
    Next
    INDEX
    Explanations

    Objective-C code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    indentation (leading whitespace) in source code, especially at the beginning of code blocks and statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on sequences of whitespace used for code indentation (leading spaces/tabs before actual code).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -1.34
    布団
    -1.28
    気になった
    -1.27
    清掃
    -1.24
    inguez
    -1.23
     '
    -1.21
    社会主义
    -1.21
    イルミネ
    -1.20
    お土産
    -1.19
    sią
    -1.18
    POSITIVE LOGITS
     Änderung
    1.28
    urization
    1.28
    axle
    1.27
    tdessen
    1.27
    mators
    1.27
     televisão
    1.26
    وازم
    1.20
     actuellement
    1.18
    鈈
    1.17
    いぐるみ
    1.16
    Activations Density 0.011%

    No Known Activations