© 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. 27377
    Prev
    Next
    INDEX
    Explanations

    contribute to

    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
    ne
    0.64
     Whom
    0.54
    macht
    0.53
     Please
    0.52
    8
    0.52
     When
    0.50
    ů
    0.50
    lig
    0.50
    le
    0.50
    νού
    0.49
    POSITIVE LOGITS
     triplicate
    0.66
    o
    0.66
    뤽
    0.61
    น
    0.61
     கண்டுபிடிக்க
    0.60
     взя
    0.57
     stata
    0.56
    ल
    0.56
     đứa
    0.55
     kabupaten
    0.54
    Activations Density 0.014%

    No Known Activations