© 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. 18242
    Prev
    Next
    INDEX
    Explanations

    expressjs

    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
     (%
    0.46
     globular
    0.42
     improves
    0.42
     (*)
    0.41
    僌
    0.41
     Adaptation
    0.40
     Improves
    0.40
     Adapt
    0.40
     Improve
    0.40
     Stress
    0.40
    POSITIVE LOGITS
    राधना
    0.46
    еве
    0.45
    옷
    0.43
    rij
    0.43
    sheep
    0.43
    規模
    0.42
    uga
    0.41
    selenium
    0.41
    ubercul
    0.40
    Meri
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.