© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10638
    Prev
    Next
    INDEX
    Explanations

    sequence of words, or }

    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
     vôtre
    -1.89
    禵
    -1.88
    poptosis
    -1.85
    ressee
    -1.85
     iſt
    -1.76
    縹
    -1.75
     esquerda
    -1.73
    Ꮴ
    -1.70
    queous
    -1.66
    Ⲉ
    -1.66
    POSITIVE LOGITS
    ’
    2.56
    s
    2.20
     in
    1.98
    )
    1.85
     inspiré
    1.73
     \\
    1.73
     as
    1.70
     or
    1.70
     all
    1.63
     entire
    1.61
    Activations Density 0.004%

    No Known Activations