© 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. 200565
    Prev
    Next
    INDEX
    Explanations

    make important strides

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

    pigeon breed

    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
    ²
    0.48
    ases
    0.48
    lig
    0.46
    ully
    0.45
     inodes
    0.45
     probability
    0.45
     possíveis
    0.45
     inland
    0.45
    assen
    0.44
    úl
    0.44
    POSITIVE LOGITS
    皋
    0.52
     Packard
    0.51
     ধরিয়
    0.51
    BROOK
    0.48
     Demonstrate
    0.47
    տր
    0.47
     DiCaprio
    0.47
     परफॉर्म
    0.47
     Picker
    0.47
    恽
    0.47
    Activations Density 0.001%

    No Known Activations