© 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. 216846
    Prev
    Next
    INDEX
    Explanations

    words with following context

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

    academic contexts and descriptors

    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
    รับ
    0.53
    पं
    0.48
    음
    0.47
    กล
    0.47
    ँ
    0.46
    에
    0.46
     roofs
    0.46
    어
    0.46
     terraces
    0.45
    Hardware
    0.45
    POSITIVE LOGITS
     entidade
    0.50
     tué
    0.49
     cinq
    0.46
     podle
    0.46
     voix
    0.46
    іл
    0.46
     bislang
    0.45
     vier
    0.45
     bisher
    0.45
    斌
    0.44
    Activations Density 0.001%

    No Known Activations