© 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. 225525
    Prev
    Next
    INDEX
    Explanations

    emojis and years

    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
    http
    1.09
     http
    1.02
     xrange
    0.62
     ২০১২
    0.61
     ২০১০
    0.59
     ২০১১
    0.58
     iPod
    0.57
    ↵
    0.52
    
    0.52
     Huffington
    0.52
    POSITIVE LOGITS
    🥰
    1.25
     ২০২২
    1.24
     🥰
    1.23
     ২০২৩
    1.21
    🥲
    1.19
     २०२
    1.17
    🫣
    1.14
    🫶
    1.13
     २०२२
    1.11
     проєкту
    1.11
    Activations Density 0.035%

    No Known Activations