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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29078
    Prev
    Next
    INDEX
    Explanations

    CodeMirror, Immutable, rules

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

    The neuron is looking for identifiers or names that begin with an uppercase letter (e.g. module or class names and other capitalized tokens).

    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
    small
    -1.36
    cera
    -1.31
    sin
    -1.30
    o
    -1.26
    re
    -1.25
    鸸
    -1.22
    ➀
    -1.21
    ジング
    -1.19
    HIGH
    -1.18
    IN
    -1.17
    POSITIVE LOGITS
    嗚
    1.52
    其實
    1.43
    或者
    1.35
     your
    1.32
    他
    1.30
    为了
    1.30
    由於
    1.27
    мѣ
    1.25
    9
    1.24
    攪
    1.24
    Activations Density 0.005%

    No Known Activations