© 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. 83121
    Prev
    Next
    INDEX
    Explanations

    cards and charts

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

    crafting bucket tracker conflicts 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
    يس
    0.57
    heureusement
    0.51
    ادة
    0.48
    ниці
    0.47
     compone
    0.46
    سة
    0.46
    𒃻
    0.46
    ائض
    0.45
     materiaal
    0.45
    ின
    0.45
    POSITIVE LOGITS
    Prince
    0.54
     Teller
    0.53
     Prince
    0.52
     Tram
    0.50
    Lc
    0.47
     PRIN
    0.46
    Princess
    0.46
     Nether
    0.46
     I
    0.45
     Elder
    0.45
    Activations Density 0.000%

    No Known Activations