© 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. 35003
    Prev
    Next
    INDEX
    Explanations

    do, done, try, create, own

    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
    葯
    0.46
     Screens
    0.44
     screens
    0.41
     Ish
    0.41
    creativecommons
    0.40
     कारक
    0.40
    場合があります
    0.40
     swimmers
    0.39
     Hayashi
    0.39
     phones
    0.38
    POSITIVE LOGITS
    ogliere
    0.43
     наконец
    0.40
    proud
    0.39
    hled
    0.39
    \
    0.38
    ани
    0.38
    がき
    0.38
     damned
    0.38
    부를
    0.38
    年初
    0.37
    Activations Density 0.000%

    No Known Activations