© 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. 99951
    Prev
    Next
    INDEX
    Explanations

    the noun

    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
    brtc
    -1.86
    푉
    -1.60
    l
    -1.58
    Funciones
    -1.54
    蜮
    -1.49
     arasındaki
    -1.48
    に関しては
    -1.45
     («
    -1.45
    奚
    -1.45
    didn
    -1.44
    POSITIVE LOGITS
     this
    1.92
     with
    1.91
     où
    1.60
     first
    1.55
    Have
    1.52
    When
    1.52
     your
    1.51
     oneself
    1.51
     lancar
    1.47
    If
    1.45
    Activations Density 0.225%

    No Known Activations