© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69973
    Prev
    Next
    INDEX
    Explanations

    case, required, additional information

    np_acts-logits-general · gemini-2.5-flash-lite

    King of England

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ક્ર
    0.47
     variar
    0.46
    ;
    0.45
    ivar
    0.42
     adequado
    0.42
    يمكن
    0.41
     lembrar
    0.41
     Oskar
    0.41
     Cunha
    0.41
     giugno
    0.40
    POSITIVE LOGITS
    is
    0.58
    ์
    0.50
     racist
    0.47
     Japanese
    0.46
    ât
    0.46
     CIRC
    0.45
     ልጅ
    0.45
    😵
    0.45
    isini
    0.44
     petri
    0.44
    Activations Density 0.000%

    No Known Activations