© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110038
    Prev
    Next
    INDEX
    Explanations

    describing states and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ホワイト
    0.45
    lig
    0.44
     ઓ
    0.44
    ಂಟು
    0.44
    घरों
    0.43
     ආකාර
    0.42
     उपस्थित
    0.42
     opção
    0.42
     पेन
    0.41
    зя
    0.41
    POSITIVE LOGITS
    while
    0.45
     while
    0.44
    หร่
    0.42
    orice
    0.42
    최
    0.41
    cherche
    0.40
    iad
    0.39
     phù
    0.38
    \}$.
    0.38
    árl
    0.37
    Activations Density 0.005%

    No Known Activations