© 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. 115522
    Prev
    Next
    INDEX
    Explanations

    numbers and specific events

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

    stone, groups, coffee cup

    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
     અધિકારી
    0.47
    फरी
    0.47
    امر
    0.46
    귿
    0.45
    ारीरिक
    0.44
    renderCamera
    0.44
    딪
    0.44
    뷔
    0.43
    QTTR
    0.43
    违法
    0.43
    POSITIVE LOGITS
     బు
    0.47
     &
    0.46
     ሃ
    0.42
     ከአ
    0.42
     premise
    0.41
     คอม
    0.41
     取っ
    0.40
     Pot
    0.40
     coffee
    0.40
     Coffee
    0.39
    Activations Density 0.001%

    No Known Activations