© 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. 139473
    Prev
    Next
    INDEX
    Explanations

    folder, mode, method

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

    starting phrases

    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
     algebraic
    0.53
     ligament
    0.44
    %
    0.44
    рованной
    0.43
     kosher
    0.42
    қ
    0.42
    빨
    0.42
     signaling
    0.42
    ām
    0.42
    SIGNAL
    0.41
    POSITIVE LOGITS
    னுடன்
    0.53
    reiche
    0.50
     高校
    0.50
     津
    0.49
    YS
    0.48
     Contreras
    0.47
     તમામ
    0.47
     單
    0.46
     प्रयासों
    0.46
     Tomlinson
    0.46
    Activations Density 0.001%

    No Known Activations