© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16330
    Prev
    Next
    INDEX
    Explanations

    granulated sugar

    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
    د
    0.80
    با
    0.79
    З
    0.77
    ”
    0.65
    ദ
    0.65
    ’
    0.65
    กับ
    0.64
    W
    0.64
    K
    0.62
    d
    0.60
    POSITIVE LOGITS
     can
    0.68
     renal
    0.62
     pared
    0.62
    ometric
    0.59
     urination
    0.58
     predation
    0.56
     евре
    0.55
     urinal
    0.55
     triathlon
    0.55
     uridine
    0.55
    Activations Density 0.006%

    No Known Activations