© 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. 62315
    Prev
    Next
    INDEX
    Explanations

    retrieved or accessed dates

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

    months and years

    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
    Clear
    0.40
     querida
    0.39
     Clear
    0.39
    ")/
    0.39
     corners
    0.38
    #
    0.38
     tzv
    0.38
    Canonical
    0.37
     pronunci
    0.37
     ormai
    0.37
    POSITIVE LOGITS
     estud
    0.46
    上网
    0.45
    逕
    0.45
     წინ
    0.45
    迳
    0.44
    的人生
    0.42
    ilir
    0.42
     문제를
    0.41
     проблеми
    0.41
     उत्सुक
    0.41
    Activations Density 0.021%

    No Known Activations