© 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. 168947
    Prev
    Next
    INDEX
    Explanations

    annual revenue

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

    positive outcomes

    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
     março
    0.50
    兵庫
    0.47
     черво
    0.47
     bilhões
    0.46
    ലെസ്
    0.45
    붉
    0.45
    祝い
    0.45
    வுகளில்
    0.44
    旅客
    0.44
    <unused2140>
    0.44
    POSITIVE LOGITS
     Cred
    0.50
    ET
    0.47
    otional
    0.47
    ci
    0.44
     pH
    0.42
     Versailles
    0.42
     Helps
    0.42
     majority
    0.42
    erce
    0.42
     Cent
    0.41
    Activations Density 0.003%

    No Known Activations