© 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. 251540
    Prev
    Next
    INDEX
    Explanations

    furnace is, promises of, awaits the

    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
    شان
    0.55
    asem
    0.52
    ،
    0.49
    都沒有
    0.46
    ر
    0.44
    ?
    0.42
     منشور
    0.41
     LPARAM
    0.41
     ferrovi
    0.41
    èbre
    0.41
    POSITIVE LOGITS
     엄
    0.46
    ফেট
    0.45
     Retired
    0.44
     recreated
    0.43
     তাঁর
    0.43
     ವರ್ಷ
    0.43
     cranks
    0.43
    ்த
    0.42
     полностью
    0.42
     ఏడాది
    0.42
    Activations Density 0.000%

    No Known Activations