© 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. 31177
    Prev
    Next
    INDEX
    Explanations

    markdown code blocks

    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
     megjelen
    -0.80
    pousada
    -0.77
     expresa
    -0.74
     atd
    -0.73
     expresses
    -0.73
    isNot
    -0.73
    brandt
    -0.73
    isEdit
    -0.72
     éstos
    -0.72
     natürlich
    -0.71
    POSITIVE LOGITS
     **
    1.55
    **
    1.55
    **(
    1.10
    ```
    1.07
    __[
    1.04
     "__
    1.01
    __
    0.98
     *
    0.98
     __
    0.96
    pong
    0.88
    Activations Density 0.004%

    No Known Activations