© 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. 144640
    Prev
    Next
    INDEX
    Explanations

    certainty and growth

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

    list item markers (2, II)

    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
    仴
    0.45
    傻
    0.43
     Ironically
    0.43
    ığında
    0.42
    ллин
    0.42
    严
    0.42
    粙
    0.42
    ‒
    0.42
    ূপে
    0.41
    严重
    0.41
    POSITIVE LOGITS
     resultant
    0.50
     expir
    0.47
     quarters
    0.47
     هو
    0.47
    acceleration
    0.46
     stimmt
    0.46
     burgeoning
    0.46
     consequent
    0.45
     acceleration
    0.44
    aksha
    0.43
    Activations Density 0.000%

    No Known Activations