© 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. 166745
    Prev
    Next
    INDEX
    Explanations

    following conditions and terms

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

    Tokyo Metropolitan Government Building

    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
     verbally
    0.47
     بالغ
    0.46
    隻
    0.46
    ärm
    0.45
    chi
    0.44
    ASE
    0.44
    ably
    0.42
    ரிக்க
    0.41
     Dupree
    0.41
    腹
    0.41
    POSITIVE LOGITS
     calificación
    0.54
     alasan
    0.52
     hatırl
    0.50
     原因
    0.49
     fatores
    0.48
     Опреде
    0.48
     hijau
    0.47
    ᶰ
    0.47
     détermination
    0.47
     sebepler
    0.46
    Activations Density 0.000%

    No Known Activations