© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7145
    Prev
    Next
    INDEX
    Explanations

    public class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hf
    0.54
     এলাক
    0.46
     amoureux
    0.44
     spalle
    0.44
    </bbox>
    0.43
    ames
    0.42
    ánchez
    0.42
     肉
    0.42
    oja
    0.41
    pointee
    0.41
    POSITIVE LOGITS
    ִ
    0.43
     inspection
    0.42
     test
    0.41
     index
    0.40
     demonic
    0.40
     approx
    0.40
     exorc
    0.40
     exercitation
    0.39
     jornada
    0.39
     testing
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.