© 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. 10431
    Prev
    Next
    INDEX
    Explanations

    dates/mathematical symbols

    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
    Dynam
    0.37
    สัง
    0.36
    CPS
    0.35
    몬
    0.35
    Brand
    0.34
    行
    0.34
    ोह
    0.33
    Dimensional
    0.33
    주
    0.33
    Trans
    0.33
    POSITIVE LOGITS
    zeniach
    0.46
     %\
    0.42
     centrifugation
    0.41
     multiplets
    0.41
    ales
    0.41
    ancellation
    0.40
     kterou
    0.40
     mastect
    0.40
     restant
    0.40
     funerals
    0.40
    Activations Density 0.018%

    No Known Activations