© 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. 107246
    Prev
    Next
    INDEX
    Explanations

    public, formation, hire

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

    transfusion transmitted infection

    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
     बंदी
    0.55
     veya
    0.54
     किंवा
    0.53
     נק
    0.52
     eller
    0.50
     또는
    0.50
     જ
    0.48
     ἢ
    0.48
     चमक
    0.48
     ж
    0.47
    POSITIVE LOGITS
     formação
    0.50
    Công
    0.50
    SELECT
    0.48
    公
    0.48
    select
    0.47
    rv
    0.47
    PUBLIC
    0.46
    Public
    0.45
    hire
    0.44
     público
    0.44
    Activations Density 0.000%

    No Known Activations