© 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. 3671
    Prev
    Next
    INDEX
    Explanations

    ratings and scores

    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
    viève
    -0.88
    nende
    -0.81
    tigma
    -0.79
     mengam
    -0.76
     memasang
    -0.75
    gesehen
    -0.75
    ㎥
    -0.74
     tanı
    -0.74
    Ghost
    -0.73
    ggior
    -0.73
    POSITIVE LOGITS
     Excellent
    2.98
     excellent
    2.92
    Excellent
    2.56
    excellent
    2.38
     Good
    2.38
     good
    2.09
     Poor
    2.05
     poor
    2.05
    Good
    1.91
     Very
    1.88
    Activations Density 0.057%

    No Known Activations