© 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. 150835
    Prev
    Next
    INDEX
    Explanations

    spare day

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

    foreign language and timeframes

    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
     assemblies
    0.50
    ル
    0.48
    );
    0.48
     Semiconductors
    0.48
     restarts
    0.47
     holders
    0.47
     electrolytes
    0.46
     requires
    0.46
     elaborate
    0.45
    RestorePolicy
    0.45
    POSITIVE LOGITS
    郏
    0.58
     Josie
    0.47
    hiya
    0.47
    espoir
    0.46
    蜷
    0.44
    辈子
    0.43
    鹫
    0.43
     karakter
    0.43
    赦
    0.43
     Terbaru
    0.42
    Activations Density 0.001%

    No Known Activations