© 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. 56818
    Prev
    Next
    INDEX
    Explanations

    staying with technical terms

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

    employment relations, battery models, inductive charging

    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
     સુધી
    0.49
    zył
    0.48
     ചെ
    0.44
    ๓
    0.43
     तक
    0.43
    ပို
    0.43
    пин
    0.42
    ပိုင်း
    0.42
     पाण्डे
    0.42
     ප්ර
    0.41
    POSITIVE LOGITS
    '
    0.51
    簡易
    0.45
     ages
    0.44
     protezione
    0.44
     sprechen
    0.43
     tors
    0.42
    𝗩
    0.42
     unterschied
    0.41
    𝗪
    0.41
    返品
    0.41
    Activations Density 0.000%

    No Known Activations