© 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. 12306
    Prev
    Next
    INDEX
    Explanations

    highest or largest in a category

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

    second largest

    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
     satisfacer
    0.45
    ন্ধে
    0.43
     particulières
    0.42
     están
    0.42
     अने
    0.42
    淖
    0.41
     unrival
    0.40
     particuliers
    0.40
    ANGO
    0.40
     araştırm
    0.40
    POSITIVE LOGITS
    ranking
    0.53
     derrière
    0.51
    behind
    0.49
    rank
    0.49
     behind
    0.48
    second
    0.47
    🥈
    0.47
    magnitude
    0.46
     ranking
    0.46
    ranked
    0.46
    Activations Density 0.042%

    No Known Activations