© 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. 100997
    Prev
    Next
    INDEX
    Explanations

    like other

    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
     as
    -1.91
     what
    -1.49
     bahkan
    -1.38
     by
    -1.37
     where
    -1.27
     =
    -1.26
     даже
    -1.24
    what
    -1.23
    imiento
    -1.23
     such
    -1.22
    POSITIVE LOGITS
     other
    2.17
    andere
    1.59
    其他的
    1.41
     další
    1.37
    faits
    1.35
     другими
    1.34
     innych
    1.34
     другая
    1.34
    eens
    1.33
     ďal
    1.31
    Activations Density 0.060%

    No Known Activations