© 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. 40889
    Prev
    Next
    INDEX
    Explanations

    education, media, health, or strategy

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

    URL, contact info, education

    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
    ot
    0.46
    PR
    0.46
     अजि
    0.45
    was
    0.44
    u
    0.44
     Principe
    0.43
    att
    0.43
     Wrestling
    0.43
    '
    0.42
    arak
    0.42
    POSITIVE LOGITS
     homen
    0.47
    ندية
    0.43
     alken
    0.42
     सिस्टम
    0.42
     internazionali
    0.41
     chatbots
    0.41
     verdadeiro
    0.41
     системы
    0.41
    מית
    0.41
    സില്‍
    0.41
    Activations Density 0.000%

    No Known Activations