© 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. 124894
    Prev
    Next
    INDEX
    Explanations

    features, frequencies, foreign words

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

    measures and specific terms

    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
    P
    0.55
    p
    0.50
     p
    0.49
    Complex
    0.46
    Imag
    0.46
    H
    0.46
    )&
    0.46
    曷
    0.45
    Das
    0.44
    M
    0.44
    POSITIVE LOGITS
     Kiy
    0.52
    ർഡ്
    0.50
    স্বাধীন
    0.45
    superblock
    0.45
     tumor
    0.44
     കഴ
    0.44
    बड़े
    0.44
     funktion
    0.44
    体积
    0.44
     সকলকে
    0.43
    Activations Density 0.002%

    No Known Activations