© 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. 38251
    Prev
    Next
    INDEX
    Explanations

    numbers and positionals

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

    foundational model or continuation

    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
    }=\
    0.50
    ט
    0.49
    خذ
    0.49
    ти
    0.47
    "));
    0.46
     beak
    0.44
    '));
    0.43
     grooms
    0.43
    ხედ
    0.42
    Team
    0.42
    POSITIVE LOGITS
     excitatory
    0.45
     graphs
    0.45
     পাপ
    0.45
    ợi
    0.43
     Kaf
    0.43
     २
    0.42
     प्रोटीन
    0.42
     थ्री
    0.42
     tubuh
    0.41
     गों
    0.41
    Activations Density 0.000%

    No Known Activations