© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52332
    Prev
    Next
    INDEX
    Explanations

    without limitation

    np_acts-logits-general · gemini-2.5-flash-lite

    appearance and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    맑
    0.46
     posi
    0.44
     marki
    0.44
     storied
    0.43
     commen
    0.43
     accompagnée
    0.42
     repayment
    0.42
     roots
    0.41
     pola
    0.41
     jaka
    0.41
    POSITIVE LOGITS
    犷
    0.47
    atch
    0.45
    otos
    0.44
     उनका
    0.43
    ීමේ
    0.42
    ölt
    0.42
     మహిళ
    0.41
     दुर्लभ
    0.41
    倛
    0.41
     अनजान
    0.41
    Activations Density 0.000%

    No Known Activations