© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14045
    Prev
    Next
    INDEX
    Explanations

    imminent danger

    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
     atualmente
    -1.39
     amanhã
    -1.30
     tø
    -1.27
     bedien
    -1.27
    </strong>
    -1.27
    currently
    -1.26
     כ
    -1.26
    还是很
    -1.24
     ninguém
    -1.23
     cuanto
    -1.23
    POSITIVE LOGITS
     of
    2.13
     from
    2.08
     to
    1.91
     on
    1.84
     and
    1.72
     for
    1.70
     by
    1.69
     into
    1.68
     with
    1.38
    ڡ
    1.38
    Activations Density 0.145%

    No Known Activations