© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3634
    Prev
    Next
    INDEX
    Explanations

    list items following quotation marks

    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
     drains
    0.59
     draining
    0.54
     drained
    0.52
     від
    0.49
     depleted
    0.48
    <unused399>
    0.47
     почув
    0.46
    тки
    0.46
     >>
    0.44
     presion
    0.44
    POSITIVE LOGITS
     nourrice
    0.49
     métier
    0.47
     seuls
    0.46
    StringSet
    0.46
    媾
    0.45
     sõ
    0.43
    异
    0.43
     mas
    0.42
     Mason
    0.42
    jenigen
    0.42
    Activations Density 0.001%

    No Known Activations