© 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. 109174
    Prev
    Next
    INDEX
    Explanations

    expression of apology

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

    apologies and refusals

    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
     mistakes
    0.61
     canceled
    0.54
    ్‌
    0.53
     emailed
    0.52
     holidays
    0.52
     bandages
    0.51
     cataracts
    0.51
     cancelled
    0.50
     faults
    0.50
     the
    0.49
    POSITIVE LOGITS
    7
    0.58
    .
    0.56
    <0xA0>
    0.54
    για
    0.52
    3
    0.52
    to
    0.51
    e
    0.50
    6
    0.50
    м
    0.50
     permettant
    0.49
    Activations Density 0.006%

    No Known Activations