© 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. 29946
    Prev
    Next
    INDEX
    Explanations

    damage is caused

    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
     takimi
    -0.77
     suhu
    -0.77
    ecirc
    -0.76
     REVIEWS
    -0.74
    iais
    -0.73
     linearized
    -0.72
    ')";
    -0.71
     biscuit
    -0.71
    ోగ
    -0.71
    igerung
    -0.70
    POSITIVE LOGITS
     damage
    5.16
     damages
    3.69
    damage
    3.64
     Damage
    3.58
    Damage
    3.47
     DAMAGE
    2.88
    DAMAGE
    2.63
     damaged
    2.41
     daño
    2.34
     daños
    2.27
    Activations Density 0.094%

    No Known Activations