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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25626
    Prev
    Next
    INDEX
    Explanations

    sector A

    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
    та
    0.56
    и
    0.53
    ор
    0.51
    в
    0.50
    ра
    0.48
    са
    0.48
    г
    0.48
    计
    0.47
    с
    0.47
    日
    0.47
    POSITIVE LOGITS
     EM
    0.47
     camels
    0.45
     marries
    0.44
     alps
    0.43
     seduce
    0.42
     Aztecs
    0.42
     discs
    0.42
     armies
    0.42
     crabs
    0.42
     snails
    0.42
    Activations Density 0.000%

    No Known Activations