© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84608
    Prev
    Next
    INDEX
    Explanations

    tokens in AI text

    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
     Rolex
    0.53
     bodily
    0.49
    樯
    0.47
     frivol
    0.46
     transferable
    0.46
     Bored
    0.45
     Poker
    0.45
     Number
    0.45
    दुल
    0.45
     Having
    0.44
    POSITIVE LOGITS
    शुदा
    0.51
    원에서
    0.44
     appelez
    0.43
     ഉ
    0.42
    t
    0.42
    unsqueeze
    0.42
    ὐ
    0.42
     بین
    0.42
     synthesize
    0.42
    |$,
    0.41
    Activations Density 0.000%

    No Known Activations