© 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. 165263
    Prev
    Next
    INDEX
    Explanations

    everything desirable

    np_acts-logits-general · gemini-2.5-flash-lite

    intros pective, long recognized

    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
    睪
    0.49
    зю
    0.48
    齙
    0.47
    нтип
    0.46
     Summers
    0.44
    ﺋ
    0.44
    Spectral
    0.43
    Republican
    0.42
    えない
    0.42
    屆
    0.42
    POSITIVE LOGITS
     осозна
    0.52
    Interface
    0.50
     مشتری
    0.48
    ীয়
    0.48
     evokes
    0.48
     playmaker
    0.47
     sứ
    0.46
     listo
    0.46
    ্ব
    0.46
     Cabe
    0.46
    Activations Density 0.000%

    No Known Activations