© 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. 239889
    Prev
    Next
    INDEX
    Explanations

    sand separating, sexy Sadie, competitive advantage, nitrogen fertilizer

    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
     resonance
    0.46
     transverse
    0.42
     derrière
    0.42
    軞
    0.41
     upto
    0.41
     genre
    0.41
    হাম্ম
    0.39
     each
    0.39
     truncated
    0.39
     Bia
    0.39
    POSITIVE LOGITS
    н
    0.54
    мин
    0.51
     நாட்ட
    0.49
    getUser
    0.48
    й
    0.46
     буду
    0.45
    рита
    0.45
    йы
    0.44
    Used
    0.44
    噼
    0.44
    Activations Density 0.000%

    No Known Activations