© 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. 243897
    Prev
    Next
    INDEX
    Explanations

    news break, term solution, embodiments 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
     cooking
    0.52
     bonding
    0.52
     mineral
    0.50
    '
    0.47
     hair
    0.46
     receipt
    0.45
     slant
    0.45
     toothbrush
    0.45
     Bonding
    0.44
    bonding
    0.44
    POSITIVE LOGITS
     permitem
    0.61
    篪
    0.60
     összef
    0.55
    等于
    0.54
     Consultez
    0.54
    ocole
    0.54
    𒈹
    0.53
     Choisissez
    0.53
     градусов
    0.52
    ৫
    0.52
    Activations Density 0.000%

    No Known Activations