© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72741
    Prev
    Next
    INDEX
    Explanations

    enumerated items in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite

    goals include, requirements, visual novel

    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
    Negative Logits
     eateries
    0.46
    ালিয়া
    0.43
    など
    0.43
    ddots
    0.43
    Zr
    0.42
    ชุด
    0.42
    λά
    0.41
    TER
    0.41
     altamente
    0.41
    凋
    0.41
    POSITIVE LOGITS
     stormy
    0.51
    itale
    0.49
     എന്നാൽ
    0.48
    ьо
    0.47
    మెంట్
    0.46
     انسان
    0.46
     камень
    0.46
     ഭാര്യ
    0.46
     quantized
    0.45
     എന്നാല്‍
    0.45
    Activations Density 0.000%

    No Known Activations