© 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. 211904
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and determiners

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

    programming examples and searches

    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
    혐
    0.51
    essence
    0.50
    뱅
    0.50
    expressing
    0.50
    げ
    0.50
    ಹಾ
    0.49
    y
    0.49
    갬
    0.49
    Ὑ
    0.47
    alnız
    0.47
    POSITIVE LOGITS
     Cerebral
    0.56
     overs
    0.52
     স্বীকৃতি
    0.48
     Ecuador
    0.46
    认知
    0.46
     brainstorm
    0.45
     awards
    0.45
     announcer
    0.45
     macron
    0.45
     reboot
    0.44
    Activations Density 0.000%

    No Known Activations