© 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. 11959
    Prev
    Next
    INDEX
    Explanations

    product qualities and performance

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

    qualities and conditions

    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
     শে
    0.47
    ျေး
    0.46
     রান্না
    0.45
     farmhouse
    0.44
    链路
    0.43
    酒精
    0.43
    粑
    0.42
    创意
    0.42
     नवीनतम
    0.42
     şeyi
    0.42
    POSITIVE LOGITS
     للغاية
    0.44
    September
    0.40
     เห็น
    0.39
    kowo
    0.38
     fulfils
    0.38
    André
    0.37
     apprehension
    0.37
    ctions
    0.36
     scalp
    0.36
    Fif
    0.36
    Activations Density 0.007%

    No Known Activations