© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    guide to resources and information

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

    guide to topics

    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
    ')
    0.43
    '
    0.43
     ad
    0.40
    '')
    0.40
     আদর
    0.39
    感激
    0.38
    ψ
    0.38
    ']
    0.38
     adecu
    0.38
     rapaz
    0.38
    POSITIVE LOGITS
     기초
    0.45
    逋
    0.44
     توا
    0.43
    玮
    0.43
     നേ
    0.42
    琹
    0.42
    Commiss
    0.41
    涞
    0.41
    ЛИ
    0.40
     Ünivers
    0.40
    Activations Density 0.001%

    No Known Activations