© 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. 188084
    Prev
    Next
    INDEX
    Explanations

    pup, town, lyrics, mind

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

    consumer demand rebound

    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
     करीब
    0.47
     пользователь
    0.46
     සඳහා
    0.45
     целях
    0.44
     найбіль
    0.44
     августа
    0.44
    ྡ
    0.44
     जिसमें
    0.43
    ônio
    0.43
    ्राष्ट
    0.43
    POSITIVE LOGITS
    ppo
    0.54
    த்தல்
    0.52
    pp
    0.51
    pping
    0.46
    ppe
    0.46
    B
    0.46
    FName
    0.45
     lup
    0.45
     erk
    0.44
    alcool
    0.44
    Activations Density 0.000%

    No Known Activations