© 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. 201984
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
    ip
    0.57
    _
    0.55
    partum
    0.54
    from
    0.54
    owned
    0.50
    unts
    0.49
    flipped
    0.48
    ’
    0.48
    employed
    0.47
    CommonAncestor
    0.47
    POSITIVE LOGITS
     nicht
    0.57
     quá
    0.54
     không
    0.50
    聲
    0.50
     Không
    0.48
     nichts
    0.48
     lanz
    0.48
     silenz
    0.47
     pequeno
    0.47
     КС
    0.46
    Activations Density 0.000%

    No Known Activations