© 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. 83972
    Prev
    Next
    INDEX
    Explanations

    localization processes

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

    average weight

    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
     멋
    0.45
    EXPECT
    0.42
     wild
    0.42
    promoting
    0.41
     homely
    0.41
     ثم
    0.41
     disappointment
    0.41
    期待
    0.40
    ~/
    0.40
     అక్కడ
    0.39
    POSITIVE LOGITS
     Насе
    0.43
    机器学习
    0.43
    込
    0.43
    公务
    0.43
     séries
    0.42
     Dewey
    0.42
     snd
    0.42
     Insc
    0.42
     prevision
    0.41
    ्व
    0.41
    Activations Density 0.001%

    No Known Activations