© 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. 34-GEMMASCOPE-RES-131K
    7. 92990
    Prev
    Next
    INDEX
    Explanations

    associated factor

    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_34/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
    osis
    -0.87
     ```
    -0.82
    //{
    -0.80
    JR
    -0.79
    ViewChild
    -0.79
    棘
    -0.78
    ahrt
    -0.78
    prepend
    -0.77
     stránka
    -0.77
    ，
    -0.77
    POSITIVE LOGITS
    內的
    0.92
    Rés
    0.84
    骞
    0.84
     Eunice
    0.82
    主題
    0.79
     creadores
    0.78
    rigues
    0.77
    nhi
    0.76
    ustice
    0.75
    теристики
    0.75
    Activations Density 0.006%

    No Known Activations