© 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. 122070
    Prev
    Next
    INDEX
    Explanations

    speedy parking

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

    more traditional or modern options

    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
     sion
    0.49
    资源
    0.48
     deprec
    0.48
     BUY
    0.48
     outages
    0.47
     thirds
    0.47
     surrender
    0.46
    ﻖ
    0.46
     età
    0.46
     除
    0.46
    POSITIVE LOGITS
    Adress
    0.47
    omorf
    0.46
    блон
    0.46
    o
    0.45
    adress
    0.44
    otham
    0.43
    Globals
    0.43
     Gebiet
    0.43
    erci
    0.42
    tempat
    0.42
    Activations Density 0.001%

    No Known Activations