© 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. 111663
    Prev
    Next
    INDEX
    Explanations

    saving options and management

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

    existing assets and projects

    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
    숫
    0.49
    BUT
    0.47
    фель
    0.47
    如果你
    0.47
    踺
    0.47
    हम
    0.46
     powerAll
    0.46
    菻
    0.45
    䍜
    0.45
    枺
    0.44
    POSITIVE LOGITS
    ],
    0.52
     Carls
    0.50
    atoren
    0.48
     caustic
    0.48
     τε
    0.46
    ış
    0.46
    ischen
    0.46
    3
    0.44
     ג
    0.44
     Υ
    0.44
    Activations Density 0.000%

    No Known Activations