© 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. 44288
    Prev
    Next
    INDEX
    Explanations

    preceded by a verb and followed by a preposition or number

    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
    thoscope
    -1.38
    Skocz
    -1.33
    </sup>
    -1.32
    。
    -1.31
     );
    -1.31
     ONLY
    -1.30
    resizingMask
    -1.29
     {}));
    -1.28
    garmin
    -1.28
     chá
    -1.28
    POSITIVE LOGITS
    kannya
    1.63
     yetu
    1.62
     nying
    1.45
     indipendente
    1.34
     związane
    1.32
    t
    1.30
     Yorkers
    1.29
    ende
    1.25
    tons
    1.23
    comings
    1.23
    Activations Density 0.067%

    No Known Activations