© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92442
    Prev
    Next
    INDEX
    Explanations

    foreign languages, alternatives

    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
    o
    0.48
    levels
    0.47
    els
    0.45
    Carr
    0.44
    est
    0.44
     n
    0.44
    Option
    0.43
    hess
    0.43
     y
    0.43
    ing
    0.43
    POSITIVE LOGITS
     ângulo
    0.59
     ovog
    0.54
     सुप्रभात
    0.54
     Asalamualaikum
    0.54
     ឬ
    0.54
     должен
    0.52
     должна
    0.52
     migli
    0.51
     curviliné
    0.51
     ovoj
    0.51
    Activations Density 0.010%

    No Known Activations