© 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. 161878
    Prev
    Next
    INDEX
    Explanations

    Jones, Buhari, pieces, condition, way, locations

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

    code symbols and file extensions

    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
    راحی
    0.54
    μενο
    0.52
    ടുത
    0.51
    ผิว
    0.48
     vesicle
    0.48
    ྜ
    0.48
     iyo
    0.48
    രോധ
    0.48
     childish
    0.47
     tyrant
    0.47
    POSITIVE LOGITS
     Зе
    0.57
     Мі
    0.54
     则
    0.51
     перший
    0.50
     лінії
    0.50
     此
    0.50
     包括
    0.50
     ମ
    0.49
     Ј
    0.48
     атмосфер
    0.47
    Activations Density 0.001%

    No Known Activations