© 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. 106496
    Prev
    Next
    INDEX
    Explanations

    triple quoted comments

    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
    cerol
    -0.85
     reivindic
    -0.80
    volver
    -0.79
     annulus
    -0.76
    arki
    -0.76
     datatype
    -0.74
    leda
    -0.73
     canais
    -0.73
     talento
    -0.72
     solute
    -0.71
    POSITIVE LOGITS
     every
    0.81
     those
    0.79
     sections
    0.75
     at
    0.74
     section
    0.72
    عف
    0.72
    vių
    0.72
     Hogg
    0.72
     Section
    0.71
    aville
    0.68
    Activations Density 0.008%

    No Known Activations