© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204848
    Prev
    Next
    INDEX
    Explanations

    neural networks and CNNs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    封
    0.46
     टेस्ट
    0.46
     kle
    0.44
     サングラス
    0.44
    楚
    0.43
    枪
    0.42
     Kurz
    0.42
     prec
    0.41
     recuperar
    0.41
    虏
    0.41
    POSITIVE LOGITS
    ,’’
    0.51
    in
    0.51
    
    0.50
    io
    0.50
    .’’
    0.49
    ມີ
    0.48
     comunitario
    0.48
    ons
    0.48
    oto
    0.47
    provide
    0.47
    Activations Density 0.002%

    No Known Activations