© 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. 195280
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and subordinate clauses

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

    medical and emotional states

    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
     राघव
    0.46
     сохра
    0.45
     حسن
    0.45
    किशोर
    0.44
     keeps
    0.43
     马
    0.43
     prudent
    0.42
     جو
    0.41
    反而
    0.41
     mediates
    0.41
    POSITIVE LOGITS
    ক
    0.52
    କ
    0.48
    ี่
    0.47
     IDENT
    0.47
    কর্ণ
    0.47
    ছের
    0.46
    বিভিন্ন
    0.46
     PROBLEMS
    0.46
    meniz
    0.45
    ্যের
    0.44
    Activations Density 0.001%

    No Known Activations