© 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. 233058
    Prev
    Next
    INDEX
    Explanations

    meeting ofdispensesmade by

    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
     repaired
    0.48
     Sereth
    0.44
    Lire
    0.43
     walkway
    0.43
    ]/
    0.42
    ஶ
    0.42
     रोजाना
    0.42
     després
    0.42
     trampled
    0.41
     glared
    0.41
    POSITIVE LOGITS
     아닌
    0.44
     Photonics
    0.42
     Explos
    0.40
    㷌
    0.40
    other
    0.39
    ('-',
    0.39
    বৃহ
    0.39
    のではない
    0.38
     иных
    0.38
    consensus
    0.38
    Activations Density 0.002%

    No Known Activations