© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 262
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, or abbreviations

    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_all/layer_41_width_262k_l0_big
    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
    <unused671>
    0.55
    .³
    0.53
    <unused328>
    0.53
    ាតុ
    0.51
    OLYBD
    0.51
    ratingBarStyle
    0.50
    IRCONIUM
    0.50
    specifiedByURL
    0.50
    <unused706>
    0.49
    jobSize
    0.48
    POSITIVE LOGITS
    1
    0.91
    2
    0.74
    5
    0.72
    0
    0.71
    3
    0.68
    4
    0.67
    9
    0.66
    0.66
    6
    0.64
    7
    0.63
    Activations Density 0.012%

    No Known Activations