© 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. 109888
    Prev
    Next
    INDEX
    Explanations

    And he

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

    if you have example

    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
    ний
    0.46
    ारों
    0.45
    桁
    0.45
    нта
    0.44
    شي
    0.44
    لن
    0.44
    няя
    0.44
     ー
    0.44
    ня
    0.43
     allé
    0.43
    POSITIVE LOGITS
    bian
    0.47
    affron
    0.47
    oload
    0.46
     indah
    0.46
    z
    0.46
    o
    0.45
    agriculture
    0.45
     Anadolu
    0.43
     "'.$
    0.43
     کمپیو
    0.43
    Activations Density 0.000%

    No Known Activations