© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1488
    Prev
    Next
    INDEX
    Explanations

    especially specific circumstances

    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_16_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
    ون
    0.38
    ot
    0.37
    З
    0.37
    ”，
    0.33
    ”،
    0.33
    》，
    0.32
    Z
    0.32
    |$,
    0.31
    kiego
    0.31
    或者是
    0.31
    POSITIVE LOGITS
     to
    0.36
    ו
    0.34
    ма
    0.33
    t
    0.33
    то
    0.31
    ASH
    0.31
    ANT
    0.31
    .
    0.30
    ALTER
    0.30
     I
    0.30
    Activations Density 0.151%

    No Known Activations