© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77928
    Prev
    Next
    INDEX
    Explanations

    travel, openings, weekend

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

    physical harm

    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
    s
    0.49
     inoc
    0.48
    ulations
    0.48
     explores
    0.48
     explore
    0.47
    _{(
    0.47
     cooperated
    0.47
    ic
    0.46
    ivalence
    0.46
    atação
    0.46
    POSITIVE LOGITS
    ﻁ
    0.52
    ﻅ
    0.47
    Speech
    0.43
    ط
    0.42
     clums
    0.41
    FocusValue
    0.40
     divisor
    0.40
    Tm
    0.40
    റ്റ
    0.39
    <0xD6>
    0.38
    Activations Density 0.001%

    No Known Activations