© 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. 21345
    Prev
    Next
    INDEX
    Explanations

    Maven build systems and handguns

    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
    逦
    -2.44
    骓
    -2.27
    骉
    -2.22
    ۉ
    -2.19
    桕
    -2.14
    ſelves
    -2.13
    慊
    -2.09
    酝
    -2.08
    laması
    -2.08
     ayud
    -2.05
    POSITIVE LOGITS
    }$
    3.17
    m
    3.11
    es
    3.02
    螄
    2.89
    in
    2.83
     be
    2.67
    {
    2.67
    蟥
    2.67
    z
    2.63
    樒
    2.55
    Activations Density 0.007%

    No Known Activations