© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3983
    Prev
    Next
    INDEX
    Explanations

    % sign in command line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cadastro
    0.84
    Посилання
    0.82
    Amit
    0.80
    இந்த
    0.79
    য়াত
    0.77
    ",$
    0.73
    Боль
    0.73
     Detalles
    0.73
    Einstellungen
    0.72
    CID
    0.72
    POSITIVE LOGITS
    ين
    0.78
    이고
    0.77
    é
    0.75
    ová
    0.72
    ح
    0.71
    ové
    0.68
    ის
    0.67
    ко
    0.67
    هم
    0.67
    نا
    0.66
    Activations Density 0.000%

    No Known Activations