© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135173
    Prev
    Next
    INDEX
    Explanations

    your Leads or threat assessment

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

    stages, layered 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
     слід
    0.51
     Listings
    0.49
     Listing
    0.48
     वस्तू
    0.48
     गोपनीय
    0.48
     忄
    0.48
     Distributions
    0.47
     Items
    0.46
    CRO
    0.46
     Dishes
    0.45
    POSITIVE LOGITS
    ç
    0.52
    su
    0.51
    đ
    0.51
    customerId
    0.50
    Figura
    0.49
    সু
    0.49
    z
    0.49
    {
    0.47
    リーナ
    0.47
    si
    0.46
    Activations Density 0.000%

    No Known Activations