© 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. 154407
    Prev
    Next
    INDEX
    Explanations

    cookies and policy

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

    simply bypassed application

    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
     pollin
    0.50
     as
    0.48
     contain
    0.46
    ある
    0.46
     mist
    0.44
     Jal
    0.44
    띠
    0.44
    ம்பு
    0.43
    ون
    0.43
    ного
    0.43
    POSITIVE LOGITS
     শুরুতে
    0.51
     åp
    0.49
     খারাপ
    0.48
     PRICES
    0.46
     खासकर
    0.46
    一开始
    0.46
    開幕
    0.46
    ና
    0.46
    prices
    0.45
     Preise
    0.45
    Activations Density 0.000%

    No Known Activations