© 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. 138304
    Prev
    Next
    INDEX
    Explanations

    flames, repairs, indoor

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

    settings and objects

    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
     agress
    0.54
     Unle
    0.51
    وط
    0.49
     manuals
    0.49
     in
    0.48
     nab
    0.47
     inns
    0.47
     e
    0.46
     Drawn
    0.46
     Happens
    0.46
    POSITIVE LOGITS
    mime
    0.52
    landscape
    0.52
    amini
    0.49
     सफ़ेद
    0.47
    ycor
    0.47
    decorative
    0.46
     此
    0.46
    cutter
    0.46
    bibinfo
    0.45
    complexity
    0.44
    Activations Density 0.002%

    No Known Activations