© 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. 233774
    Prev
    Next
    INDEX
    Explanations

    fiscal year

    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
     (
    0.54
     على
    0.54
    ستون
    0.51
     on
    0.50
     موجب
    0.50
    }$&$-
    0.50
     Expenditure
    0.50
    ρηση
    0.50
     لكم
    0.49
    iquée
    0.49
    POSITIVE LOGITS
     cleansing
    0.45
    국의
    0.45
    อากาศ
    0.44
    สรร
    0.44
     refresh
    0.43
     rebellious
    0.43
     atténuées
    0.43
    ☄
    0.43
    intensité
    0.43
     효과
    0.42
    Activations Density 0.001%

    No Known Activations