© 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. 26556
    Prev
    Next
    INDEX
    Explanations

    specific words following numbers or "the"

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

    generating or needing systems/processes

    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
    थ
    0.46
    亚马
    0.45
    结
    0.43
    毛
    0.43
     Тео
    0.42
    ament
    0.42
     बढ़ते
    0.42
    国外
    0.42
     похо
    0.41
     Lúc
    0.41
    POSITIVE LOGITS
     stadium
    0.50
    0
    0.50
     antiserum
    0.49
     toegang
    0.49
     fai
    0.47
    ည
    0.47
     gates
    0.45
     siège
    0.45
     doet
    0.45
     gì
    0.44
    Activations Density 0.000%

    No Known Activations