© 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. 6091
    Prev
    Next
    INDEX
    Explanations

    revealed revealed try released by bring distance

    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
     நூற்ற
    0.44
    افي
    0.44
    ariye
    0.43
    ۵
    0.43
     Iod
    0.43
     Emission
    0.41
    ያንዳ
    0.41
     Hoch
    0.40
    ००
    0.40
     Produced
    0.40
    POSITIVE LOGITS
     mexican
    0.49
     prive
    0.43
     gaussian
    0.42
     european
    0.41
     shall
    0.39
     zom
    0.39
     badass
    0.39
    ט
    0.39
     комі
    0.38
     кли
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.