© 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. 72357
    Prev
    Next
    INDEX
    Explanations

    free lists, bottle feeding

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

    liminal spaces and interiors

    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
    raster
    0.51
    probe
    0.47
    ಸ
    0.44
    sime
    0.44
    Rajasthan
    0.44
    ম
    0.43
    সন
    0.42
    <0xB8>
    0.42
    sms
    0.42
    ever
    0.42
    POSITIVE LOGITS
     entreg
    0.47
     объекты
    0.46
     trafi
    0.46
    īd
    0.46
     khẩu
    0.46
     сторон
    0.46
    各项
    0.46
     remem
    0.45
     Möglich
    0.45
    咡
    0.45
    Activations Density 0.001%

    No Known Activations