© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102239
    Prev
    Next
    INDEX
    Explanations

    Python programming contexts

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

    Python code, particularly imports, class definitions, and test cases.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    1
    -1.36
    0
    -1.30
    fer
    -1.16
    IVERSITY
    -1.14
     especially
    -1.13
     including
    -1.13
    ";
    -1.10
     ("
    -1.06
     and
    -1.05
     hvil
    -1.05
    POSITIVE LOGITS
    delicious
    1.27
     Ulu
    1.23
     Deeds
    1.22
    ㈲
    1.21
    饃
    1.21
    negara
    1.20
     sez
    1.20
    pygame
    1.20
    䔀
    1.20
     Disponible
    1.20
    Activations Density 0.086%

    No Known Activations