© 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. 138621
    Prev
    Next
    INDEX
    Explanations

    technical and descriptive terms

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

    building systems

    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
    l
    0.51
     infert
    0.46
    t
    0.46
     علاج
    0.45
     soud
    0.44
    ično
    0.44
     aparecen
    0.43
     metoda
    0.43
    ări
    0.43
    bak
    0.42
    POSITIVE LOGITS
    мі
    0.47
    िसोदिया
    0.44
    PLAYER
    0.44
     ದಾ
    0.44
    бран
    0.43
    Hudson
    0.43
    OUGHT
    0.43
    🔪
    0.42
     GALLERY
    0.41
    REND
    0.41
    Activations Density 0.000%

    No Known Activations