© 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. 58593
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

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

    instructions or directions

    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
     সঙ্গী
    0.50
     gamanam
    0.46
    誣
    0.46
     velič
    0.43
     paket
    0.43
     financiers
    0.43
     nourrice
    0.43
    JE
    0.42
    襁
    0.42
    FECT
    0.41
    POSITIVE LOGITS
    increasing
    0.52
    yaxis
    0.48
    an
    0.46
    input
    0.45
    n
    0.45
    ức
    0.44
    rugada
    0.44
    occas
    0.43
    October
    0.43
    а
    0.43
    Activations Density 0.000%

    No Known Activations