© 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. 169822
    Prev
    Next
    INDEX
    Explanations

    presented evidence or testimonials

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

    influence and describes power dynamics

    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
    €™
    0.48
    udsman
    0.46
    isotope
    0.46
    putted
    0.46
    thisStudent
    0.45
    вича
    0.45
    umber
    0.45
    
    0.45
    вий
    0.45
    isotopes
    0.45
    POSITIVE LOGITS
     INVEST
    0.45
     Markdown
    0.44
     Handbook
    0.43
    項目
    0.43
     Solvent
    0.43
     rend
    0.42
     geçer
    0.42
     Liquid
    0.42
     Business
    0.42
     infect
    0.42
    Activations Density 0.000%

    No Known Activations