© 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. 115089
    Prev
    Next
    INDEX
    Explanations

    suppliers, president

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

    file menu commands

    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
    ཋ
    0.49
    ទទ
    0.48
    蓣
    0.47
    beni
    0.46
    űt
    0.46
    招待
    0.45
     اوكي
    0.45
     dissati
    0.45
     ըն
    0.45
     exceptions
    0.44
    POSITIVE LOGITS
    losti
    0.51
    il
    0.49
    ilim
    0.46
    іл
    0.46
    λί
    0.44
    im
    0.43
    å
    0.41
    اں
    0.40
    وَ
    0.40
    که
    0.40
    Activations Density 0.001%

    No Known Activations