© 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. 66106
    Prev
    Next
    INDEX
    Explanations

    subject to the following conditions

    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
     its
    -1.98
    THERS
    -1.42
     gwaran
    -1.39
    plante
    -1.35
    在我的
    -1.34
    dekat
    -1.33
    ROLLER
    -1.29
     bordado
    -1.29
    bague
    -1.27
    umpulkan
    -1.27
    POSITIVE LOGITS
    is
    1.27
    abetes
    1.27
    ll
    1.26
    ali
    1.16
    iv
    1.15
    cha
    1.15
    k
    1.15
     sehari
    1.15
    N
    1.14
    in
    1.13
    Activations Density 0.001%

    No Known Activations