© 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. 67145
    Prev
    Next
    INDEX
    Explanations

    cash points later

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

    ancient lore and trending news

    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
    A
    0.53
    AIN
    0.51
    А
    0.51
    Т
    0.49
    AL
    0.49
    RO
    0.48
    SE
    0.48
    К
    0.48
    Д
    0.48
    З
    0.48
    POSITIVE LOGITS
     kemarin
    0.53
     araşt
    0.49
     sonra
    0.48
    ্ডার
    0.47
     später
    0.47
     bestimmten
    0.46
     überprüfen
    0.45
     mungkin
    0.45
     développe
    0.45
    чена
    0.44
    Activations Density 0.001%

    No Known Activations