© 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. 27178
    Prev
    Next
    INDEX
    Explanations

    largely or in part

    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
    ｀)
    -1.33
    sometimes
    -1.27
     możliwe
    -1.27
    Eglise
    -1.23
    々な
    -1.20
    ピアス
    -1.20
     possible
    -1.17
    🫃
    -1.17
     grotte
    -1.16
     changé
    -1.16
    POSITIVE LOGITS
    f
    1.41
    ok
    1.40
    ac
    1.37
     also
    1.21
     what
    1.20
    os
    1.20
    b
    1.20
    N
    1.16
     удачи
    1.16
    re
    1.16
    Activations Density 0.031%

    No Known Activations