© 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. 112290
    Prev
    Next
    INDEX
    Explanations

    following prepositions or directives

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

    sections, lists, and breakdowns

    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
     คณิต
    0.48
     grips
    0.46
     ನಿರ್
    0.45
     구
    0.45
     Histor
    0.45
     Prefecture
    0.44
     gripper
    0.44
     Nomad
    0.44
     Azi
    0.44
     Nim
    0.43
    POSITIVE LOGITS
    巉
    0.46
    الة
    0.43
     बेटर
    0.42
    вого
    0.41
    ություն
    0.41
    ائية
    0.40
     ponctu
    0.40
    愛情
    0.39
    wisdom
    0.39
    ucionales
    0.38
    Activations Density 0.002%

    No Known Activations