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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1795
    Prev
    Next
    INDEX
    Explanations

    URLs and dates

    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_16k_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
    (".");
    0.45
    .”.
    0.43
     图片
    0.41
    囯
    0.40
    Includes
    0.40
     ይህም
    0.40
    bursement
    0.39
    ว์
    0.39
    ুল্য
    0.39
    📸
    0.39
    POSITIVE LOGITS
     đêm
    0.52
    capable
    0.47
    _
    0.46
    day
    0.46
     T
    0.45
     changements
    0.45
     morning
    0.45
    __
    0.44
    T
    0.43
     அன்று
    0.41
    Activations Density 0.030%

    No Known Activations