© 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. 116507
    Prev
    Next
    INDEX
    Explanations

    Quoted titles or phrases

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

    financial and relationship advice

    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
     сен
    0.46
    ס
    0.45
     그랬
    0.44
    лее
    0.44
     deliberations
    0.44
    yml
    0.43
    6
    0.43
    ert
    0.42
    inp
    0.42
     decrees
    0.42
    POSITIVE LOGITS
     useContext
    0.47
    铀
    0.46
    }"/>
    0.46
     Girlfriend
    0.46
    Cómo
    0.44
     warms
    0.44
     enrich
    0.43
    Fur
    0.43
     व्यक्तिगत
    0.43
    Wild
    0.42
    Activations Density 0.002%

    No Known Activations