© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105114
    Prev
    Next
    INDEX
    Explanations

    VLC Media Player

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    $,
    0.63
    ne
    0.59
    A
    0.55
    Value
    0.54
    AnimationFrame
    0.54
    an
    0.54
     Hakone
    0.54
    Field
    0.53
    k
    0.53
     Argonne
    0.53
    POSITIVE LOGITS
    изо
    0.68
    リム
    0.66
    ש
    0.65
    ير
    0.65
    ਰ
    0.59
    бор
    0.58
    사
    0.58
    то
    0.57
    ита
    0.57
    ли
    0.57
    Activations Density 0.000%

    No Known Activations