© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    date followed by colon

    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
    5
    0.55
    מ
    0.52
     claramente
    0.52
    込む
    0.50
    วล
    0.50
     matematica
    0.48
    ત્ર
    0.47
     VILL
    0.47
     establece
    0.46
    ండ
    0.45
    POSITIVE LOGITS
    o
    0.51
    OfWeek
    0.49
    出
    0.48
    inters
    0.45
    出した
    0.45
     disturbances
    0.44
    ini
    0.44
     of
    0.43
     Brah
    0.43
     and
    0.43
    Activations Density 0.009%

    No Known Activations