© 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. 121570
    Prev
    Next
    INDEX
    Explanations

    extended interview

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

    list item markers or focus symbols

    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
    oppers
    0.50
    ↵↵↵↵↵↵↵↵↵↵↵
    0.45
    тные
    0.44
    igas
    0.44
    hiba
    0.44
    ونها
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
     carattere
    0.42
     sustancias
    0.41
    ↵↵↵↵↵↵↵↵↵↵
    0.41
    POSITIVE LOGITS
    弈
    0.53
    𝗶
    0.48
     Shipbuilding
    0.46
     Tube
    0.45
    Wars
    0.45
    У
    0.44
    盖
    0.44
    瑄
    0.44
    ränkt
    0.43
    Д
    0.43
    Activations Density 0.000%

    No Known Activations