© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7790
    Prev
    Next
    INDEX
    Explanations

    single letters followed by specific words

    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_12_width_262k_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
    서
    0.90
    いた
    0.84
    து
    0.79
    نا
    0.77
    ся
    0.76
    ductory
    0.70
    ח
    0.66
    ようになる
    0.65
    ך
    0.63
    ли
    0.63
    POSITIVE LOGITS
    asında
    0.75
    oğlu
    0.68
    ra
    0.66
    ulously
    0.66
    ações
    0.66
    ar
    0.65
    damaged
    0.64
    gå
    0.63
    ỡng
    0.62
    radas
    0.61
    Activations Density 0.190%

    No Known Activations