© 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. 33296
    Prev
    Next
    INDEX
    Explanations

    cocaine drug use

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

    potentially omitted

    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
     Frankie
    0.47
     Cole
    0.45
     Filed
    0.45
     Those
    0.44
     Pension
    0.43
    竄
    0.43
     Dip
    0.43
     Kobe
    0.42
     ذكر
    0.42
     Jodie
    0.42
    POSITIVE LOGITS
    الوجی
    0.55
    umap
    0.54
    薢
    0.54
     montagna
    0.53
    صیٰ
    0.52
    nout
    0.52
    Antaeotricha
    0.51
     wooded
    0.51
    راہ
    0.49
    fastq
    0.49
    Activations Density 0.001%

    No Known Activations