© 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. 15174
    Prev
    Next
    INDEX
    Explanations

    default and usually

    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
     extraordin
    -1.21
     čier
    -1.11
    aing
    -1.10
    蟶
    -1.10
    WARDS
    -1.09
    据说
    -1.08
    barrow
    -1.08
     chimie
    -1.08
    如图
    -1.06
    Singles
    -1.05
    POSITIVE LOGITS
     used
    1.29
    EFAULT
    1.20
    ".
    1.13
     подготовка
    1.08
    from
    1.04
    也就
    1.04
     usually
    1.03
     found
    1.02
     wünschen
    1.00
    This
    0.98
    Activations Density 0.113%

    No Known Activations