© 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. 84932
    Prev
    Next
    INDEX
    Explanations

    responsible for

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

    your advice and needs

    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
    过后
    0.52
     sechs
    0.50
     διάρκ
    0.50
     造
    0.49
     過
    0.48
     প্রতিনিধি
    0.48
     ομά
    0.48
     τὸν
    0.48
    後的
    0.47
     zehn
    0.46
    POSITIVE LOGITS
    у
    0.56
    ام
    0.48
     Morley
    0.47
    i
    0.47
    ể
    0.46
     nave
    0.45
    ‰
    0.45
    core
    0.45
     Veuillez
    0.45
    navigationItem
    0.43
    Activations Density 0.000%

    No Known Activations