© 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. 73140
    Prev
    Next
    INDEX
    Explanations

    specific phrase beginnings

    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
    {
    -1.97
    }$,
    -1.70
    噩
    -1.63
    瓛
    -1.63
    “
    -1.62
    ```
    -1.60
    にん
    -1.55
     WIL
    -1.55
    ,\\
    -1.52
    </b>
    -1.50
    POSITIVE LOGITS
     striving
    1.80
     for
    1.60
    مرة
    1.57
    あります
    1.56
    ありますが
    1.55
    éndose
    1.55
     trying
    1.53
     undeniably
    1.53
     some
    1.49
     how
    1.49
    Activations Density 0.007%

    No Known Activations