© 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. 216428
    Prev
    Next
    INDEX
    Explanations

    government, jersey, camera, network

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

    charismatic leader, contracts, hex, pyaudio, boob

    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
     World
    0.48
    ဃ
    0.47
     x
    0.46
     nightmares
    0.44
     precludes
    0.43
     bows
    0.43
     spectator
    0.43
     V
    0.42
     lumps
    0.42
     filmp
    0.41
    POSITIVE LOGITS
    reliant
    0.53
    ses
    0.52
    Draft
    0.51
    Hex
    0.50
    Ciudad
    0.49
    ون
    0.48
    Car
    0.47
    draft
    0.47
    雙
    0.47
    calibur
    0.46
    Activations Density 0.001%

    No Known Activations