© 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. 245842
    Prev
    Next
    INDEX
    Explanations

    invited faculty

    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
    យ
    0.55
     يا
    0.54
     untested
    0.52
     použ
    0.52
     craz
    0.51
     blatantly
    0.49
     usare
    0.49
    ية
    0.49
     صارت
    0.48
     yeah
    0.47
    POSITIVE LOGITS
    诸多
    0.45
     ወቅ
    0.44
    EI
    0.43
    Bour
    0.42
    े
    0.42
    getHours
    0.41
    Rounding
    0.40
    贲
    0.40
    不仅
    0.40
    file
    0.39
    Activations Density 0.000%

    No Known Activations