© 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. 71527
    Prev
    Next
    INDEX
    Explanations

    perform or enjoy

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

    snapshots, build, simple, little, model, essentially, tour, sense, remainder

    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
    gx
    0.50
    t
    0.50
    meth
    0.48
    motion
    0.44
    9
    0.44
    த்துள்ளது
    0.43
    notify
    0.43
     Caucus
    0.43
    reet
    0.43
    methylation
    0.43
    POSITIVE LOGITS
     ස
    0.54
     દ
    0.51
     เส
    0.47
    ಗೊಳ
    0.46
     mesmer
    0.45
     ග
    0.44
     दि
    0.44
     selezion
    0.44
     dég
    0.44
     ക
    0.43
    Activations Density 0.000%

    No Known Activations