© 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. 205947
    Prev
    Next
    INDEX
    Explanations

    healthy weight, coup, support

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

    identity theft or botnets

    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
    Negative Logits
    Numbers
    0.48
     precedence
    0.43
    Conflict
    0.43
    บ
    0.42
    Quality
    0.42
     {};
    0.42
     sé
    0.41
    同样
    0.41
    Nobody
    0.41
     Carey
    0.41
    POSITIVE LOGITS
    žila
    0.48
    avaju
    0.48
     연료
    0.48
     pasien
    0.47
    ：
    0.47
    assanam
    0.46
     rebate
    0.46
    cigarette
    0.45
     karbon
    0.45
     Heiz
    0.44
    Activations Density 0.000%

    No Known Activations