© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84245
    Prev
    Next
    INDEX
    Explanations

    lists, statements, definitions

    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
     schematically
    0.55
    ᱗
    0.43
     luôn
    0.42
     FIG
    0.41
    6
    0.41
    தய
    0.40
    จิต
    0.40
    на
    0.40
    igenschaften
    0.40
    त्रि
    0.39
    POSITIVE LOGITS
     Ecco
    0.42
     Exceptions
    0.41
    Guesses
    0.41
     집에
    0.41
    Verbose
    0.39
    Passwords
    0.38
    疣
    0.38
    它
    0.38
     alone
    0.37
     گیا
    0.37
    Activations Density 0.020%

    No Known Activations