© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14956
    Prev
    Next
    INDEX
    Explanations

    progress and potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     his
    -1.88
     jego
    -1.23
     years
    -1.22
    (/^
    -1.21
     zijn
    -1.18
     himself
    -1.14
    ▂
    -1.13
    ografi
    -1.10
     he
    -1.09
     gwar
    -1.05
    POSITIVE LOGITS
     ourselves
    1.69
     we
    1.65
     our
    1.62
    我们
    1.31
     μας
    1.27
     budeme
    1.23
    んだよ
    1.20
     this
    1.19
    alım
    1.09
    anggil
    1.09
    Activations Density 0.039%

    No Known Activations