© 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. 9221
    Prev
    Next
    INDEX
    Explanations

    points reached after a delay

    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
     not
    -1.94
     both
    -1.79
     is
    -1.52
     không
    -1.46
     with
    -1.46
    とは思
    -1.44
    不仅
    -1.40
    咫
    -1.39
     ۸
    -1.38
    を書いて
    -1.29
    POSITIVE LOGITS
     of
    1.74
     to
    1.70
    ја
    1.60
    ’
    1.55
     it
    1.41
     чтобы
    1.39
     sondern
    1.37
     Acerca
    1.37
    ')
    1.35
    ]$.
    1.35
    Activations Density 0.035%

    No Known Activations