© 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. 184599
    Prev
    Next
    INDEX
    Explanations

    historical or factual information

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

    foundation of

    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
    ளர்
    0.47
    dert
    0.45
     positioning
    0.43
    liest
    0.43
     explicitly
    0.43
     to
    0.42
    lide
    0.42
    蹭
    0.42
    lerin
    0.42
     zmienia
    0.42
    POSITIVE LOGITS
    ut
    0.54
    Macros
    0.51
    ون
    0.50
    ពួក
    0.48
    icur
    0.47
     cottages
    0.45
     квітня
    0.45
    Selections
    0.44
     libertà
    0.44
     पत्नी
    0.44
    Activations Density 0.001%

    No Known Activations