© 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. 125211
    Prev
    Next
    INDEX
    Explanations

    real time, questions comments

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

    stable, biased downwards

    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
    問
    0.54
     грани
    0.51
     sultan
    0.51
    สน
    0.49
     biti
    0.48
    協力
    0.47
     ponctu
    0.46
     tani
    0.45
    エンド
    0.45
     Niz
    0.45
    POSITIVE LOGITS
    vom
    0.55
    iOS
    0.54
    \%).
    0.50
    yuan
    0.47
    physiology
    0.47
     实现
    0.46
     locis
    0.46
     Audiobook
    0.45
    cemia
    0.45
     Technol
    0.45
    Activations Density 0.000%

    No Known Activations