© 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. 10-GEMMASCOPE-RES-131K
    7. 73397
    Prev
    Next
    INDEX
    Explanations

    narrow passages or specific senses

    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
     Sosten
    -1.78
    𖣘
    -1.78
    ⇴
    -1.74
     Dois
    -1.72
     indepen
    -1.70
    дово
    -1.69
     Egyes
    -1.68
    Shown
    -1.62
     Luar
    -1.61
     Temos
    -1.59
    POSITIVE LOGITS
    ).
    2.59
    s
    2.34
    3
    2.20
    t
    2.16
     narrow
    2.14
    \
    2.14
    \_
    2.11
    !)
    1.88
    c
    1.88
    .)
    1.88
    Activations Density 0.023%

    No Known Activations