© 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. 127549
    Prev
    Next
    INDEX
    Explanations

    medical dosage and antibiotic

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

    processing and analysis

    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
     mixers
    0.48
     NRI
    0.43
     Bomber
    0.41
     Comcast
    0.41
     vs
    0.40
    áže
    0.40
     hitting
    0.40
    u
    0.40
     NPA
    0.40
    uhi
    0.39
    POSITIVE LOGITS
     wspom
    0.54
     இருக்கலாம்
    0.49
     섹
    0.45
     مذکور
    0.44
    从业
    0.44
     desta
    0.43
     bénéf
    0.43
    쎄
    0.43
     dieser
    0.43
     존재하는
    0.43
    Activations Density 0.002%

    No Known Activations