© 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. 87853
    Prev
    Next
    INDEX
    Explanations

    literature and history concepts

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

    literature and history discussions

    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
    اللہ
    0.48
    Якщо
    0.47
    ଢ
    0.47
     communists
    0.46
     flared
    0.45
    riwal
    0.44
    बम
    0.44
     daripada
    0.44
     explosives
    0.44
    Ꭳ
    0.44
    POSITIVE LOGITS
     تاریخ
    0.49
     letteratura
    0.49
    业界
    0.48
     literatura
    0.48
     literature
    0.47
     Literature
    0.47
     Faculté
    0.46
     Historia
    0.45
     ولا
    0.45
    Literature
    0.45
    Activations Density 0.001%

    No Known Activations