© 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. 43560
    Prev
    Next
    INDEX
    Explanations

    Elite: Dangerous exploration

    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
    ati
    0.50
    acceleration
    0.49
    lag
    0.49
    ل
    0.49
    precise
    0.49
    ال
    0.48
    collision
    0.48
    ین
    0.47
    editing
    0.47
    amplitude
    0.46
    POSITIVE LOGITS
     অতিথ
    0.48
     medlem
    0.48
    娃
    0.47
     erhältlich
    0.47
     erfüll
    0.47
     товары
    0.47
    ский
    0.45
    兑
    0.45
     khen
    0.44
     மக்களை
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.