© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71584
    Prev
    Next
    INDEX
    Explanations

    mention what, prove you, highlight these

    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_10/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
    Only
    -1.22
    <bos>
    -1.21
     jedynie
    -1.20
     pouze
    -1.20
     между
    -1.18
     only
    -1.16
     тільки
    -1.16
     mediodía
    -1.15
    only
    -1.15
     только
    -1.14
    POSITIVE LOGITS
     your
    2.03
     then
    1.34
     any
    1.34
     yourself
    1.26
     with
    1.25
    ığınız
    1.24
     when
    1.19
    valida
    1.16
    ar
    1.13
     using
    1.13
    Activations Density 0.167%

    No Known Activations