© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42690
    Prev
    Next
    INDEX
    Explanations

    item number

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

    gpt-3.5-turbo

    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
     않았
    0.54
     જુ
    0.50
     늘
    0.47
    WEBPACK
    0.46
    concentration
    0.45
     임
    0.44
     כי
    0.44
     мо
    0.44
     सम्मिलित
    0.44
    medical
    0.42
    POSITIVE LOGITS
     Extras
    0.52
     Loot
    0.46
     Challenge
    0.46
    กี
    0.46
     Roswell
    0.46
    يل
    0.46
     extras
    0.46
     composers
    0.46
     Skinner
    0.46
     upkeep
    0.45
    Activations Density 0.001%

    No Known Activations