© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 254111
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    स्कृतिक
    0.45
     పరిస్థి
    0.41
    ப்படுகிறது
    0.41
     culturais
    0.41
    प्लो
    0.40
     पत्नी
    0.40
    哿
    0.39
    ტორი
    0.39
    逻
    0.39
    $)$.
    0.39
    POSITIVE LOGITS
     drawback
    0.60
     thing
    0.57
     factor
    0.57
     mistake
    0.56
     objective
    0.55
     distinction
    0.54
     caveat
    0.54
    *
    0.51
     difference
    0.50
     hallmark
    0.50
    Activations Density 0.039%

    No Known Activations