© 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. 201849
    Prev
    Next
    INDEX
    Explanations

    networking book title format

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

    space, room, or distance

    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
     می‌کنند
    0.53
    ology
    0.48
    语法
    0.47
     Linguistic
    0.46
     Listener
    0.46
     Grammar
    0.46
     Theology
    0.46
     学
    0.46
     Geology
    0.45
     Neuroscience
    0.45
    POSITIVE LOGITS
     calmly
    0.49
     spear
    0.48
     incarcer
    0.47
     strained
    0.46
    らん
    0.45
     antique
    0.45
     inundated
    0.45
     compressive
    0.44
     injure
    0.44
     colliding
    0.43
    Activations Density 0.001%

    No Known Activations