© 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. 169648
    Prev
    Next
    INDEX
    Explanations

    following 'silent', 'after', 'highest'

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

    available country statistics

    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
    BlockUsed
    0.55
     กิน
    0.55
    $\--
    0.54
     взрослых
    0.54
    กิน
    0.51
    чених
    0.51
     ROUILLER
    0.50
     аба
    0.50
    мога
    0.50
     животных
    0.49
    POSITIVE LOGITS
    p
    0.59
    o
    0.57
    ter
    0.54
    hm
    0.54
    main
    0.52
    h
    0.51
    pe
    0.48
    drama
    0.48
    bar
    0.47
    issue
    0.47
    Activations Density 0.001%

    No Known Activations