© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113311
    Prev
    Next
    INDEX
    Explanations

    testicular cancers and function

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

    names of specific geographic locations or parts of the body.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    9
    -2.88
    '
    -2.86
    o
    -2.69
     "
    -2.66
     dasarnya
    -2.59
    h
    -2.34
    1
    -2.34
    k
    -2.11
    荸
    -2.06
     ludzie
    -2.03
    POSITIVE LOGITS
    .
    3.06
    髏
    2.66
    媗
    2.61
    apatalk
    2.52
    ,“
    2.34
     disminuir
    2.31
    甡
    2.31
    の変化
    2.27
    、“
    2.25
    CHREIB
    2.25
    Activations Density 0.004%

    No Known Activations