© 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. 184494
    Prev
    Next
    INDEX
    Explanations

    at [company/location]

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

    conveys information or purpose

    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
     Clive
    0.46
    شتی
    0.46
    などを
    0.43
    তরে
    0.43
    のカ
    0.43
    のス
    0.42
    علان
    0.42
    鿌
    0.42
     BSc
    0.42
    等を
    0.41
    POSITIVE LOGITS
     мебели
    0.46
     afflict
    0.44
    Latch
    0.42
    Imports
    0.41
    일상
    0.40
     belts
    0.40
    Roaming
    0.40
     gooey
    0.40
    грева
    0.39
     свят
    0.39
    Activations Density 0.001%

    No Known Activations