© 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. 88325
    Prev
    Next
    INDEX
    Explanations

    body typesfirst useincludes aira hefty

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

    signal, force, basic, fmt, &&

    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
     resembling
    0.47
     immobili
    0.45
    翰
    0.45
     satisf
    0.44
    <b>
    0.44
    *
    0.44
    
    0.44
    ED
    0.43
     themed
    0.43
     ult
    0.42
    POSITIVE LOGITS
    getNext
    0.51
    சு
    0.50
    useState
    0.49
     заменить
    0.49
    NotExist
    0.48
    બી
    0.48
    UISelectors
    0.47
    ない
    0.47
    compId
    0.46
    Ⴊ
    0.46
    Activations Density 0.000%

    No Known Activations