© 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. 37600
    Prev
    Next
    INDEX
    Explanations

    accretion and limit

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

    units of time and conditional statements

    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
     doigts
    0.47
    得
    0.45
    মাণ
    0.43
     pouvons
    0.42
     常
    0.42
     vuol
    0.42
    ത്തിന്റെയും
    0.42
    avate
    0.41
    xel
    0.41
    得多
    0.41
    POSITIVE LOGITS
     예배
    0.46
    АР
    0.44
    Назад
    0.44
    𝗢
    0.44
    骷
    0.43
     પોસ્ટ
    0.43
    ENG
    0.42
     ريا
    0.42
    лас
    0.41
    禮
    0.41
    Activations Density 0.000%

    No Known Activations