© 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. 115049
    Prev
    Next
    INDEX
    Explanations

    progressive folk

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

    handling scams and discretion

    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
    اهای
    0.50
     slits
    0.49
    ന
    0.48
    子の
    0.47
    YYYY
    0.46
    perror
    0.46
    트를
    0.46
    人を
    0.45
    azah
    0.45
    ians
    0.44
    POSITIVE LOGITS
    LER
    0.46
    мп
    0.45
     органи
    0.45
     м
    0.44
    馇
    0.43
     бактери
    0.43
     главы
    0.42
     пап
    0.42
    він
    0.42
    滪
    0.41
    Activations Density 0.001%

    No Known Activations