© 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. 25658
    Prev
    Next
    INDEX
    Explanations

    It used to be

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

    Andy Weir books

    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
    Př
    0.52
     stronę
    0.49
    盻
    0.48
     teorías
    0.47
    <unused3>
    0.47
    รอบ
    0.47
     близо
    0.46
     পরিবর্তিত
    0.46
    LastError
    0.45
    女儿
    0.45
    POSITIVE LOGITS
     |
    0.50
     traffic
    0.48
     centenary
    0.46
     transport
    0.46
     visibility
    0.45
     affordability
    0.44
     vehicles
    0.44
     pack
    0.43
     afford
    0.42
     vehicle
    0.42
    Activations Density 0.001%

    No Known Activations