© 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. 48895
    Prev
    Next
    INDEX
    Explanations

    enjoy it

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

    insoluble, originated, IUPAC

    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
    ლების
    0.54
    tp
    0.54
    Wij
    0.53
    ס
    0.52
    கடந்த
    0.50
    serial
    0.50
    typal
    0.50
     Politik
    0.49
    囯
    0.49
     Nicolás
    0.49
    POSITIVE LOGITS
     bulging
    0.50
     harrowing
    0.47
     blindness
    0.46
     passion
    0.45
     acre
    0.45
     shik
    0.45
     acoustic
    0.45
     eyesight
    0.45
    haro
    0.45
     aflat
    0.45
    Activations Density 0.000%

    No Known Activations