© 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. 86969
    Prev
    Next
    INDEX
    Explanations

    writing and publishing content

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

    Hindi, generic, and specific terms

    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
    ര്‍ക്കും
    0.46
     ஹைட்
    0.45
    ைக
    0.45
    ség
    0.44
    ദ്ധതി
    0.43
     पुस्तकें
    0.43
    𒆷
    0.42
     mód
    0.41
    मिक
    0.41
     संगीत
    0.41
    POSITIVE LOGITS
     Wei
    0.45
    Wei
    0.44
     Authority
    0.43
    мии
    0.40
     Passage
    0.40
     ALL
    0.39
    万
    0.38
     Levels
    0.38
     wei
    0.38
     Min
    0.38
    Activations Density 0.002%

    No Known Activations