© 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. 73631
    Prev
    Next
    INDEX
    Explanations

    on foot or praying

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

    manufacture and warfare

    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
    otherArchive
    0.45
    壹章
    0.44
     Carnaval
    0.42
     indépend
    0.42
     valable
    0.42
     danach
    0.42
     drugo
    0.42
    哟
    0.42
    τικά
    0.41
    ওয়
    0.41
    POSITIVE LOGITS
     타이
    0.50
     แก
    0.45
    DES
    0.44
    DB
    0.44
    cac
    0.42
    lia
    0.42
     최고의
    0.41
    DO
    0.41
    、
    0.41
    fuels
    0.40
    Activations Density 0.000%

    No Known Activations