© 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. 56802
    Prev
    Next
    INDEX
    Explanations

    if you

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

    homophobic or misfortune

    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
    тна
    0.50
    恴
    0.50
    𝙜
    0.49
    gewicht
    0.49
    歎
    0.48
    onte
    0.46
     этот
    0.46
    페이지
    0.44
    е
    0.44
    бо
    0.44
    POSITIVE LOGITS
    نی
    0.55
     adenosine
    0.47
     ethylene
    0.47
     methylation
    0.47
     deno
    0.47
    ید
    0.46
     indole
    0.46
    ری
    0.45
     carboxylic
    0.44
     vineyards
    0.44
    Activations Density 0.000%

    No Known Activations