© 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. 144977
    Prev
    Next
    INDEX
    Explanations

    opening lists

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

    opening or adjusting settings

    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
    ojana
    0.44
    侢
    0.44
    dsl
    0.43
    kai
    0.42
    oq
    0.42
     spesial
    0.42
    bett
    0.42
    ensington
    0.41
    padded
    0.40
    舛
    0.40
    POSITIVE LOGITS
     aprire
    0.47
     Dummy
    0.46
     ก็
    0.46
     மலை
    0.46
     அழை
    0.45
     Einstellungen
    0.45
     öffnen
    0.44
    เปิด
    0.44
     เปิด
    0.44
     목록
    0.43
    Activations Density 0.002%

    No Known Activations