© 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. 10-GEMMASCOPE-RES-131K
    7. 13978
    Prev
    Next
    INDEX
    Explanations

    names and special characters

    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_10/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
     using
    -2.89
     regarding
    -2.75
     believes
    -2.72
     putting
    -2.69
     helped
    -2.69
     countless
    -2.64
     makes
    -2.63
     before
    -2.56
     during
    -2.53
     Since
    -2.53
    POSITIVE LOGITS
    锨
    2.67
     Dinas
    2.44
     strikingly
    2.42
     acclaimed
    2.42
     delightfully
    2.38
    commonly
    2.36
    鸸
    2.36
     captivating
    2.36
     unbelievably
    2.34
     ridiculously
    2.31
    Activations Density 0.012%

    No Known Activations