© 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. 47394
    Prev
    Next
    INDEX
    Explanations

    in good hands or safe

    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
     engrossed
    -0.83
    ḥ
    -0.78
    zub
    -0.74
    norr
    -0.74
    لومات
    -0.73
     recomiendo
    -0.73
     potrebné
    -0.72
    тиво
    -0.72
    Mask
    -0.72
    codes
    -0.71
    POSITIVE LOGITS
     capable
    2.36
     safe
    2.20
    safe
    1.88
     competent
    1.69
    capable
    1.57
     hands
    1.52
     trustworthy
    1.48
     experienced
    1.45
     trusted
    1.39
     incapable
    1.35
    Activations Density 0.029%

    No Known Activations