© 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-16K
    7. 11875
    Prev
    Next
    INDEX
    Explanations

    photography, discharge, medications, compressor

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

    regularization, algebra, plan, code, combination

    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_16k_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
     one
    0.44
     barons
    0.43
    議員
    0.41
     برای
    0.41
     به
    0.41
     храм
    0.40
    ⿸
    0.40
    ها
    0.40
    ची
    0.40
    ลง
    0.40
    POSITIVE LOGITS
    🌗
    0.45
    ździer
    0.41
    <unused0>
    0.40
    consumption
    0.39
    stånd
    0.39
    ver
    0.39
    headings
    0.39
    inguishable
    0.38
    mittent
    0.38
    ствующие
    0.38
    Activations Density 0.004%

    No Known Activations