© 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. 59268
    Prev
    Next
    INDEX
    Explanations

    essay, submit, sepsis, harming

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

    going faster

    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
    נ
    0.56
     органов
    0.53
     engen
    0.49
    आर
    0.49
     öğrenc
    0.48
    ängen
    0.48
     internationalen
    0.47
    ҥ
    0.47
    ění
    0.46
     öğrenciler
    0.46
    POSITIVE LOGITS
    s
    0.57
    warning
    0.54
    puce
    0.52
    cris
    0.52
    putation
    0.52
    nor
    0.51
    test
    0.50
    smile
    0.50
    Pipeline
    0.50
    names
    0.49
    Activations Density 0.000%

    No Known Activations