© 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. 147621
    Prev
    Next
    INDEX
    Explanations

    duration and specific drugs

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

    horrific crime and abuse

    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
    stein
    0.48
    meta
    0.47
     لاحظ
    0.47
     அற்புதமான
    0.47
    butterfly
    0.46
    kanal
    0.46
    Brett
    0.45
     ਕੀਤਾ
    0.45
    🥸
    0.44
    braith
    0.44
    POSITIVE LOGITS
     campaigners
    0.48
     activists
    0.46
     mechanics
    0.45
     particles
    0.45
     disruptive
    0.45
     impractical
    0.45
     prejudices
    0.45
     neighbourhoods
    0.45
     neighborhoods
    0.44
     failings
    0.44
    Activations Density 0.000%

    No Known Activations