© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77708
    Prev
    Next
    INDEX
    Explanations

    Natural News, cookbook, qualified

    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
     while
    -0.89
     several
    -0.86
     because
    -0.85
     through
    -0.84
     strengthen
    -0.84
     after
    -0.80
     offered
    -0.79
     causing
    -0.79
    おわりに
    -0.77
     at
    -0.77
    POSITIVE LOGITS
    beng
    0.99
    ouverture
    0.89
    née
    0.85
     MRC
    0.85
    jusqu
    0.84
     waz
    0.84
    Brock
    0.83
    olving
    0.82
    PubMed
    0.82
    Epic
    0.82
    Activations Density 0.006%

    No Known Activations