© 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. 129137
    Prev
    Next
    INDEX
    Explanations

    super.onCreate

    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
     její
    -1.19
    🩴
    -1.10
    確認ください
    -1.09
    orithm
    -1.09
    Ẩ
    -1.06
    ⿺
    -1.05
    vlád
    -1.05
    pasti
    -1.04
    řez
    -1.04
     its
    -1.04
    POSITIVE LOGITS
    According
    1.23
    It
    1.17
    v
    1.08
    ↵
    1.00
    u
    0.98
    w
    0.97
    Six
    0.95
    This
    0.94
     réessayer
    0.94
     –
    0.93
    Activations Density 0.001%

    No Known Activations