© 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. 115290
    Prev
    Next
    INDEX
    Explanations

    common word followed by specific terms

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

    especially considering its size

    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
    еха
    0.49
    OrDefault
    0.48
    િ
    0.48
     어린이
    0.47
     казни
    0.45
    Volkswagen
    0.44
    AUTOM
    0.44
    𝗂
    0.44
    PlatformImage
    0.44
    בּ
    0.44
    POSITIVE LOGITS
    rzez
    0.41
     Reels
    0.41
     yelled
    0.40
     Pike
    0.40
    rious
    0.40
     diantaranya
    0.40
     Recherche
    0.39
     UBND
    0.39
     painstakingly
    0.39
    lists
    0.39
    Activations Density 0.000%

    No Known Activations