© 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. 11630
    Prev
    Next
    INDEX
    Explanations

    compare, unbeatable, improvise, apart

    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
    )”.
    1.68
    ер
    1.63
    )
    1.55
    ิ
    1.46
    ).
    1.45
    д
    1.44
    )」
    1.42
    ара
    1.41
    .}$
    1.38
    )،
    1.36
    POSITIVE LOGITS
    y
    2.88
    u
    2.78
    er
    2.52
    al
    2.48
    el
    2.47
    et
    2.47
    i
    2.47
    at
    2.31
    o
    2.25
    en
    2.22
    Activations Density 0.004%

    No Known Activations