© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18679
    Prev
    Next
    INDEX
    Explanations

    specializing in system designing

    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_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
     interoper
    0.43
    现在的
    0.41
    。
    0.40
    vdash
    0.39
     subconscious
    0.39
    the
    0.39
    在
    0.39
     subcutaneous
    0.38
     als
    0.38
     pauses
    0.38
    POSITIVE LOGITS
    ROR
    0.54
    Items
    0.50
    😰
    0.49
    IRONMENT
    0.49
    ान
    0.47
     haci
    0.47
    Wage
    0.46
    JG
    0.46
    :...
    0.46
     didn
    0.45
    Activations Density 0.001%

    No Known Activations