© 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. 33119
    Prev
    Next
    INDEX
    Explanations

    predicting next words or phrases

    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
     move
    0.45
     Ros
    0.42
    .
    0.39
     ठोस
    0.39
     of
    0.39
     stage
    0.39
     prospect
    0.37
     comprom
    0.37
     confl
    0.37
     pristine
    0.37
    POSITIVE LOGITS
     പോലുള്ള
    0.46
    Ϲ
    0.45
    weiser
    0.44
     επίσης
    0.43
    étaient
    0.43
    yser
    0.42
    她们
    0.42
    之间的
    0.41
     Anyone
    0.40
    flowLayoutPanel
    0.40
    Activations Density 0.002%

    No Known Activations