© 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. 632
    Prev
    Next
    INDEX
    Explanations

    code snippets structure or continuation

    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
    is
    0.79
    ن
    0.79
    in
    0.70
    ل
    0.70
    al
    0.66
    s
    0.65
    il
    0.64
    ש
    0.64
    م
    0.64
    es
    0.63
    POSITIVE LOGITS
    4
    0.87
    9
    0.82
    2
    0.82
    3
    0.76
    5
    0.75
    6
    0.73
    8
    0.68
    :
    0.66
    7
    0.66
    .
    0.58
    Activations Density 0.189%

    No Known Activations