© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92482
    Prev
    Next
    INDEX
    Explanations

    or in other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SVM
    0.49
    <0xE2>
    0.40
     záb
    0.40
     nightlife
    0.39
    隨
    0.39
    ↵
    0.38
    ̉i
    0.38
     इंटीग्रेशन
    0.37
    ML
    0.37
     Aut
    0.37
    POSITIVE LOGITS
     অথবা
    0.54
     अथवा
    0.54
     અથવા
    0.53
     אך
    0.49
    ἢ
    0.46
    )=-\
    0.46
     или
    0.46
     ឬ
    0.46
    assara
    0.46
     alebo
    0.45
    Activations Density 0.014%

    No Known Activations