© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30052
    Prev
    Next
    INDEX
    Explanations

    bytes and testing code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nr
    -0.77
     विक
    -0.76
    VW
    -0.73
     seines
    -0.72
    arity
    -0.71
     VW
    -0.68
    arischen
    -0.67
    ⃝
    -0.67
    ITEMS
    -0.67
     raz
    -0.67
    POSITIVE LOGITS
    dresser
    0.74
    neta
    0.73
     separator
    0.68
     Mecca
    0.67
    syst
    0.67
     Krieger
    0.67
    patrol
    0.66
     Réalisation
    0.65
    miracle
    0.64
     giro
    0.63
    Activations Density 0.071%

    No Known Activations