© 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. 68200
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

    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
     kathol
    -1.29
    ˂
    -1.24
    onomous
    -1.21
     pēc
    -1.21
     ;
    -1.20
    onekana
    -1.20
    Referenties
    -1.19
    pantalón
    -1.18
    atshirt
    -1.16
     vė
    -1.15
    POSITIVE LOGITS
     should
    1.23
     without
    1.20
    🏗
    1.20
     any
    1.07
     must
    1.02
     from
    1.02
    🥽
    0.98
     яйцо
    0.97
     leveraging
    0.97
     bolster
    0.97
    Activations Density 0.233%

    No Known Activations