© 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. 201364
    Prev
    Next
    INDEX
    Explanations

    phrases with specific following tokens

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

    list of parts

    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
    পি
    0.45
    C
    0.43
     Languages
    0.42
    si
    0.42
    U
    0.42
    රක
    0.41
    Jest
    0.41
    use
    0.41
    Hourly
    0.41
    test
    0.40
    POSITIVE LOGITS
     ክፍል
    0.54
     ठ
    0.53
     сезона
    0.53
     получил
    0.52
     ర
    0.51
     һ
    0.51
     пр
    0.51
     אחד
    0.50
     पहला
    0.50
     ஒரே
    0.50
    Activations Density 0.000%

    No Known Activations