© 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. 198157
    Prev
    Next
    INDEX
    Explanations

    free promotions

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

    all forces or groups

    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
     ót
    0.50
     doğru
    0.50
     ച
    0.47
     estructura
    0.46
     corretamente
    0.46
     ท
    0.46
     ragione
    0.46
    нской
    0.45
    碐
    0.45
     veracity
    0.45
    POSITIVE LOGITS
    ched
    0.54
    the
    0.52
    ailability
    0.50
    ang
    0.50
    ervices
    0.48
    preneur
    0.48
    avila
    0.47
    cu
    0.47
    0
    0.46
    reducing
    0.46
    Activations Density 0.000%

    No Known Activations