© 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. 12-GEMMASCOPE-2-RES-262K
    7. 4001
    Prev
    Next
    INDEX
    Explanations

    and

    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
    د
    0.93
    если
    0.88
    ość
    0.88
     Jeżeli
    0.88
    𝘬
    0.86
    frü
    0.85
    ethylsulfanyl
    0.84
    ości
    0.83
    wq
    0.83
    ди
    0.82
    POSITIVE LOGITS
    '
    1.03
     concisely
    0.97
     and
    0.91
     are
    0.84
     in
    0.82
     accordingly
    0.81
     to
    0.80
    ’
    0.78
     for
    0.74
     across
    0.74
    Activations Density 0.550%

    No Known Activations