© 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. 245145
    Prev
    Next
    INDEX
    Explanations

    animals, diverse groups, deadlines, and entertainment

    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
     développer
    0.49
    的发
    0.49
    '
    0.48
    mag
    0.47
     udvik
    0.47
    Proced
    0.47
     developer
    0.46
     نم
    0.46
    نین
    0.46
    czyć
    0.46
    POSITIVE LOGITS
    掍
    0.53
    ключения
    0.47
    ἅ
    0.46
     inscriptions
    0.44
     constellations
    0.43
     tropes
    0.43
    тину
    0.43
    GRID
    0.43
     voids
    0.43
    щую
    0.42
    Activations Density 0.001%

    No Known Activations