© 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. 36559
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

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

    numbers and punctuation

    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
    ין
    0.41
    经销
    0.41
     uguale
    0.40
    retien
    0.40
    იან
    0.40
    榈
    0.40
     สัก
    0.39
     sanded
    0.39
     derivs
    0.38
    ircon
    0.38
    POSITIVE LOGITS
     алы
    0.40
    嘗
    0.40
    其
    0.37
     automakers
    0.36
     architekt
    0.36
     daug
    0.36
    除了
    0.35
     Filipinos
    0.35
     Lern
    0.35
    邢
    0.35
    Activations Density 0.000%

    No Known Activations