© 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. 17402
    Prev
    Next
    INDEX
    Explanations

    similarities and precedents

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

    similaire, similar, analogous

    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
    endment
    0.40
    myCollision
    0.39
    ریشن
    0.38
    '};
    0.38
    𝒌
    0.38
     ব্যায়াম
    0.37
     odstr
    0.37
    converter
    0.36
    '];
    0.36
    FileDialog
    0.36
    POSITIVE LOGITS
     precedent
    0.63
     similaire
    0.61
     precedents
    0.60
     ähn
    0.57
     similar
    0.56
     이번
    0.56
     similares
    0.55
    이번
    0.54
     аналоги
    0.54
     비슷한
    0.54
    Activations Density 0.177%

    No Known Activations