© 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. 22-GEMMASCOPE-RES-131K
    7. 65629
    Prev
    Next
    INDEX
    Explanations

    to get

    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
     also
    -1.25
     también
    -1.18
     It
    -1.16
     '',
    -1.15
    also
    -1.09
     If
    -1.06
     Its
    -1.05
    ஓ
    -1.05
    eo
    -1.04
     Эти
    -1.04
    POSITIVE LOGITS
    Literally
    1.33
    まさかの
    1.19
    スポンサーリンク
    1.17
    えっ
    1.16
    是怎么回事
    1.13
     proberen
    1.13
    ﮨ
    1.13
     télévis
    1.12
     やすい
    1.07
    鄴
    1.07
    Activations Density 0.071%

    No Known Activations