© 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. 14749
    Prev
    Next
    INDEX
    Explanations

    checks if conditions

    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
    -1.84
    ，“
    -1.67
    :

    -1.64
     "--
    -1.64
    _"
    -1.59
     ("
    -1.59
     "|
    -1.56
    :"
    -1.56
     competición
    -1.54
    它
    -1.52
    POSITIVE LOGITS
     determinado
    1.56
    ﾆ
    1.47
     there
    1.47
     組
    1.45
     löytyy
    1.38
     જે
    1.34
     in
    1.31
     nėra
    1.30
    łoż
    1.30
    姹
    1.26
    Activations Density 0.017%
    No Known Activations