© 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. 49891
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers

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

    bibliographic and technical terms

    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
    waf
    0.46
     ওয়েবসাইট
    0.46
     distancing
    0.45
     বরং
    0.45
     busca
    0.44
     calmed
    0.44
    `;
    0.43
    eleaf
    0.43
     playlist
    0.43
    דות
    0.42
    POSITIVE LOGITS
     обязательно
    0.45
     ஒன்றாகும்
    0.40
     ライト
    0.39
     michael
    0.38
    天上
    0.38
     prohibitions
    0.38
     話
    0.38
     어린
    0.38
     Chirurgien
    0.38
     besonder
    0.38
    Activations Density 0.001%

    No Known Activations