© 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. 31-GEMMASCOPE-2-RES-262K
    7. 112349
    Prev
    Next
    INDEX
    Explanations

    helpful phrases and individual circumstances

    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_31_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
     原子
    0.57
     plufieurs
    0.54
    )».
    0.53
    ぬい
    0.52
    <unused497>
    0.52
     ohmic
    0.50
     isomorphisms
    0.49
    шила
    0.49
    硣
    0.49
    ScheduledAction
    0.48
    POSITIVE LOGITS
    er
    0.58
    et
    0.49
    '
    0.48
    p
    0.48
    in
    0.46
    type
    0.45
    or
    0.45
    .
    0.44
    isk
    0.43
     Stand
    0.43
    Activations Density 0.006%

    No Known Activations