© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1005
    Prev
    Next
    INDEX
    Explanations

    This time spans

    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
     with
    -2.23
     for
    -2.05
     in
    -2.02
     from
    -1.65
     like
    -1.65
     through
    -1.63
     by
    -1.63
    ꪔ
    -1.49
     first
    -1.46
    棪
    -1.41
    POSITIVE LOGITS
     these
    1.65
    k
    1.49
     veya
    1.47
    }
    1.41
    ze
    1.39
    f
    1.39
    and
    1.38
     permitiendo
    1.36
    ;
    1.34
    ar
    1.34
    Activations Density 0.082%

    No Known Activations