© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 106916
    Prev
    Next
    INDEX
    Explanations

    directives and technical states

    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
    ໄຂ
    0.68
    lines
    0.65
    ⺝
    0.64
    츠
    0.63
    کنندگان
    0.63
    ຕິດຕໍ່
    0.62
    ών
    0.61
    ής
    0.61
    ंनो
    0.61
    lies
    0.60
    POSITIVE LOGITS
    e
    1.13
    f
    1.00
    a
    0.95
    h
    0.93
    b
    0.93
    p
    0.91
    v
    0.91
    j
    0.90
    r
    0.79
    t
    0.75
    Activations Density 0.000%

    No Known Activations