© 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. 141288
    Prev
    Next
    INDEX
    Explanations

    two events, shadow box

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

    subject followed by verb

    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
    i
    0.46
    ,'
    0.45
    te
    0.43
    kam
    0.42
    ,"
    0.41
    ioned
    0.40
    ifiably
    0.40
    -'
    0.39
     BSc
    0.39
     жо
    0.39
    POSITIVE LOGITS
     divisor
    0.52
     introducción
    0.49
     conductors
    0.48
     redire
    0.48
     sprintf
    0.47
     divisors
    0.47
     combinación
    0.47
     caracteres
    0.47
     răz
    0.47
     servicemen
    0.46
    Activations Density 0.000%

    No Known Activations