© 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. 224014
    Prev
    Next
    INDEX
    Explanations

    marketing or recipes

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

    music box or spam classification

    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
    c
    0.48
    p
    0.46
    LLY
    0.45
    C
    0.44
    त
    0.44
    VII
    0.43
    s
    0.43
    Y
    0.43
    b
    0.43
     change
    0.43
    POSITIVE LOGITS
     meeste
    0.51
     spezi
    0.50
     meisten
    0.50
     größte
    0.48
     Christensen
    0.47
     //$
    0.46
     hauptsächlich
    0.46
     laufen
    0.46
     spezielle
    0.45
     evidencias
    0.45
    Activations Density 0.002%

    No Known Activations