© 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. 70687
    Prev
    Next
    INDEX
    Explanations

    find the exact resolution

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

    finding enough

    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
     کیسے
    0.52
     publiques
    0.47
    ریض
    0.46
    何况
    0.46
    糗
    0.46
    崤
    0.46
    뜰
    0.45
    何时
    0.44
     কিরূপে
    0.43
    结束后
    0.43
    POSITIVE LOGITS
     żad
    0.51
     ct
    0.50
     directly
    0.50
     you
    0.49
    Ming
    0.48
     ),
    0.47
     se
    0.46
     suav
    0.46
     himself
    0.46
    Ft
    0.46
    Activations Density 0.001%

    No Known Activations