© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    description This

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

    document outlines

    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
     なかっ
    0.47
    ুহ
    0.40
     errori
    0.39
    Ꮓ
    0.39
    
    0.39
    あえず
    0.39
     واذا
    0.38
     kiedy
    0.38
    賂
    0.38
    newState
    0.38
    POSITIVE LOGITS
    This
    0.62
    Course
    0.53
     This
    0.53
     Course
    0.52
    这座
    0.46
    Imm
    0.46
    Teach
    0.46
    该
    0.46
    本项目
    0.45
    Protect
    0.45
    Activations Density 0.006%

    No Known Activations