© 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. 18663
    Prev
    Next
    INDEX
    Explanations

    foreign words, codes, or specific names

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

    explaining emergent phenomena or behaviors

    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
    ギフト
    0.44
    如果是
    0.43
    當
    0.43
    )?
    0.42
    wick
    0.42
    няў
    0.42
     ষে
    0.40
    ਾਬ
    0.40
     والے
    0.40
    ków
    0.39
    POSITIVE LOGITS
     inéd
    0.45
     realtime
    0.42
     permanec
    0.42
     coord
    0.42
     focussed
    0.42
     cuaderno
    0.41
     inhoud
    0.40
     نئی
    0.40
     mooi
    0.40
     lâng
    0.39
    Activations Density 0.000%

    No Known Activations