© 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. 19900
    Prev
    Next
    INDEX
    Explanations

    from understanding to manageable

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

    determine, generate, describe concepts

    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
     також
    0.52
    pictureBox
    0.52
    ΙΚ
    0.50
    יש
    0.48
     shudder
    0.47
     ಪುಸ್ತಕ
    0.46
    ｨ
    0.46
    Ми
    0.46
    🏷
    0.46
    Listo
    0.46
    POSITIVE LOGITS
    里
    0.47
     ambiance
    0.45
    头上
    0.45
    ages
    0.44
     tempat
    0.44
     elegan
    0.43
     aul
    0.43
    僧
    0.43
     Cinta
    0.42
     Ero
    0.42
    Activations Density 0.000%

    No Known Activations