© 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. 69958
    Prev
    Next
    INDEX
    Explanations

    or, approved, disregard

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

    planning infrastructure

    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
     கர்
    0.47
    エース
    0.45
    مكن
    0.42
     conhecido
    0.42
     कर्नाटक
    0.41
    プラ
    0.40
    不仅仅
    0.40
    エ
    0.40
     کرمان
    0.39
    業
    0.39
    POSITIVE LOGITS
    oooo
    0.46
     जीतकर
    0.45
     المجموعة
    0.44
    oooooooo
    0.44
    örd
    0.43
    iteit
    0.42
    ___________
    0.42
    ôts
    0.42
    ＼
    0.42
    endeu
    0.42
    Activations Density 0.000%

    No Known Activations