© 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. 180367
    Prev
    Next
    INDEX
    Explanations

    loved ones, Eastside, pie throwing

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

    calculating steps and phases

    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
    nam
    0.49
    getSave
    0.47
    郸
    0.45
    <-
    0.44
    cyber
    0.44
    peace
    0.44
    nf
    0.44
    arrows
    0.44
    い
    0.43
    &&
    0.43
    POSITIVE LOGITS
     Chakra
    0.50
     Chemicals
    0.45
     Conductivity
    0.45
     Beziehungen
    0.44
     Temperature
    0.43
     Processor
    0.42
     Proteins
    0.42
     AGE
    0.41
     Ingredients
    0.41
    ించాడు
    0.41
    Activations Density 0.001%

    No Known Activations