© 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. 251553
    Prev
    Next
    INDEX
    Explanations

    statistical, currency, reports

    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
     cave
    0.50
     majestic
    0.50
     méthodes
    0.50
    鵜
    0.50
     magyar
    0.48
    莽
    0.47
     mattina
    0.47
     componenti
    0.47
     mekanisme
    0.47
     potere
    0.46
    POSITIVE LOGITS
    t
    0.55
    m
    0.50
     관심을
    0.48
    usión
    0.48
    appt
    0.48
    rón
    0.47
    ائرة
    0.47
    Chú
    0.46
    wunsch
    0.46
    ampl
    0.45
    Activations Density 0.000%

    No Known Activations