© 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. 127746
    Prev
    Next
    INDEX
    Explanations

    Los Angeles, London, ASEAN

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

    Aerial phenomena, INFO, identify

    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
     ましょう
    0.53
    óg
    0.52
    ...</
    0.52
    esha
    0.48
    rud
    0.47
     apologized
    0.46
    ales
    0.46
    ulers
    0.46
    ud
    0.45
    elope
    0.45
    POSITIVE LOGITS
    Components
    0.54
    Materials
    0.51
     participaron
    0.51
     Excav
    0.50
    ຜະລິດຕະພັນ
    0.50
    蚬
    0.49
    LONDON
    0.49
     ASEAN
    0.49
    Period
    0.48
    Artwork
    0.48
    Activations Density 0.000%

    No Known Activations