© 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. 39959
    Prev
    Next
    INDEX
    Explanations

    interim government or roles

    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
    雱
    -2.72
     pokud
    -2.48
    禇
    -2.30
    </td>
    -2.27
     erwähnten
    -2.20
     Bedürfn
    -2.19
    jdons
    -2.17
    勦
    -2.17
     сказала
    -2.14
    灃
    -2.14
    POSITIVE LOGITS
    k
    3.69
    h
    3.17
    ise
    2.98
    ization
    2.94
    The
    2.69
    will
    2.61
    x
    2.58
    l
    2.52
    蓠
    2.50
    time
    2.47
    Activations Density 0.005%

    No Known Activations