© 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. 57053
    Prev
    Next
    INDEX
    Explanations

    STATE and dates

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bö
    -0.74
    štění
    -0.71
     Shorter
    -0.69
    utilities
    -0.68
    useful
    -0.68
    των
    -0.68
     خلال
    -0.66
     nór
    -0.65
     navn
    -0.65
     useful
    -0.65
    POSITIVE LOGITS
     Rev
    0.76
    mmers
    0.70
    bmp
    0.65
     teles
    0.65
     AY
    0.64
    angu
    0.64
     postre
    0.64
     Maj
    0.62
    Destino
    0.61
     мона
    0.60
    Activations Density 0.045%

    No Known Activations