© 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. 23637
    Prev
    Next
    INDEX
    Explanations

    URLs leading to commercial sites

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

    data-dependent, cuts, 2024

    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
    🫶
    1.02
     ২০২২
    0.96
    🥲
    0.96
    🥹
    0.93
    🫡
    0.90
     २०२२
    0.89
    🤍
    0.86
     metaverse
    0.85
     🥰
    0.82
    🥰
    0.82
    POSITIVE LOGITS
    http
    0.48
    
    0.45
    普及
    0.40
     बिज़
    0.40
     http
    0.40
     चलाया
    0.39
     Redskins
    0.39
    ddagger
    0.39
    盅
    0.38
    鼈
    0.38
    Activations Density 0.002%

    No Known Activations