© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    to someone or something

    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
    '
    -2.44
    ﮦ
    -1.78
     '
    -1.77
    蚰
    -1.66
    ?'
    -1.64
     kurzem
    -1.56
    wendige
    -1.55
     ランプ
    -1.55
     счастли
    -1.55
     is
    -1.55
    POSITIVE LOGITS
     you
    2.22
     Here
    2.13
    orescence
    2.11
     Especially
    2.06
     Usually
    2.05
     Although
    1.95
     Particularly
    1.94
     Owing
    1.84
    culoskeletal
    1.84
    akaran
    1.83
    Activations Density 0.020%

    No Known Activations