© 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. 7314
    Prev
    Next
    INDEX
    Explanations

    over 50 crowd

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

    ages and life stages

    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
    yar
    0.43
     ଭ
    0.42
     ringan
    0.39
    q
    0.39
    em
    0.38
    access
    0.38
    thermal
    0.38
     components
    0.38
    qe
    0.38
     definitions
    0.38
    POSITIVE LOGITS
    늙
    0.51
     남자
    0.46
     주로
    0.46
     जवान
    0.45
     मर्द
    0.44
     maturing
    0.44
     किशोर
    0.44
    男人
    0.43
    男子
    0.43
    hombre
    0.43
    Activations Density 0.000%

    No Known Activations