© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43874
    Prev
    Next
    INDEX
    Explanations

    original, different, unusual, novel concepts

    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
    <bos>
    -1.68
     Perſ
    -1.61
     Reſ
    -1.45
    _
    -1.45
     costruire
    -1.42
     donnant
    -1.38
     évit
    -1.38
    图源
    -1.37
     móg
    -1.35
     Conſ
    -1.32
    POSITIVE LOGITS
     but
    1.86
     if
    1.73
     while
    1.66
     although
    1.59
     still
    1.57
     as
    1.51
    ticultural
    1.38
    كية
    1.36
     use
    1.30
     maintain
    1.30
    Activations Density 0.058%

    No Known Activations