© 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. 250853
    Prev
    Next
    INDEX
    Explanations

    ancient Indian temples and art

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    梱包
    0.47
     प्रतीक
    0.45
     बुजुर्ग
    0.43
     patriarchal
    0.43
    ποίη
    0.43
    쾰
    0.42
     Lichtenfels
    0.42
    اہد
    0.41
     patriarch
    0.41
    EndInit
    0.41
    POSITIVE LOGITS
     উৎক
    0.46
     Silk
    0.46
     ADA
    0.44
    Silk
    0.43
    Blo
    0.43
     Camb
    0.42
    Tax
    0.42
    anga
    0.42
     Sog
    0.41
    <u>
    0.41
    Activations Density 0.038%

    No Known Activations