© 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. 172590
    Prev
    Next
    INDEX
    Explanations

    Global Markets

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

    Summarize or describe 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
    涳
    0.50
     கூடிய
    0.49
     deaminase
    0.48
    foon
    0.47
    NRC
    0.46
    Fuj
    0.46
    PPI
    0.46
    Fuse
    0.46
    Ꭲ
    0.45
     fourn
    0.44
    POSITIVE LOGITS
     Summary
    0.48
     caffe
    0.47
     CAD
    0.44
     revelation
    0.44
    u
    0.43
     Code
    0.43
    ü
    0.42
     cái
    0.42
     (.
    0.42
     summary
    0.42
    Activations Density 0.000%

    No Known Activations