© 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. 220139
    Prev
    Next
    INDEX
    Explanations

    historical civilizations

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

    event volume, witnessed . , research our, questions like, models about, have any

    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
     trasferimento
    0.55
    SERVICIO
    0.53
    𝗬
    0.51
    VER
    0.50
    TRANSFER
    0.50
    DELETE
    0.50
    SCREEN
    0.50
    DejaVu
    0.49
    MOVEMENT
    0.49
    ﻯ
    0.49
    POSITIVE LOGITS
     Maryland
    0.49
    ழ்ப
    0.48
    čních
    0.47
     George
    0.46
    क्सन
    0.46
     nickel
    0.46
     alternative
    0.46
     plugs
    0.45
     orphans
    0.45
     Tennessee
    0.45
    Activations Density 0.001%

    No Known Activations