© 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. 186507
    Prev
    Next
    INDEX
    Explanations

    payment and home services

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

    lid and tapas

    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
     কাট
    0.44
     букме
    0.44
    रव
    0.44
     कठ
    0.43
    %，
    0.43
     Ман
    0.43
     Гар
    0.43
    都没
    0.42
    烺
    0.42
    键
    0.42
    POSITIVE LOGITS
     Dlatego
    0.44
     Beding
    0.43
     familie
    0.43
     Dafür
    0.43
     clinics
    0.43
     famiglia
    0.42
    ia
    0.41
    bgColor
    0.40
    azepam
    0.40
     clinic
    0.40
    Activations Density 0.001%

    No Known Activations