© 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. 22906
    Prev
    Next
    INDEX
    Explanations

    methods to do

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

    large scale 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
    <0xEA>
    0.52
    Departure
    0.49
    <html>
    0.45
     contents
    0.44
    춘
    0.44
    list
    0.43
    yr
    0.43
    ло
    0.43
    Giov
    0.43
    mob
    0.43
    POSITIVE LOGITS
     bilden
    0.48
     mencegah
    0.47
     ἐν
    0.44
     čin
    0.43
     ricordare
    0.43
     克
    0.42
     制
    0.42
     necesariamente
    0.42
    糾
    0.41
     jouent
    0.41
    Activations Density 0.000%

    No Known Activations