© 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. 76751
    Prev
    Next
    INDEX
    Explanations

    locations and services

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

    variables and code snippets

    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
    जन
    0.48
    犯罪
    0.48
     आजीवन
    0.46
    если
    0.46
    世界上
    0.46
     nejen
    0.45
     crimen
    0.45
    把
    0.45
     बरत
    0.45
     दलित
    0.44
    POSITIVE LOGITS
     HPLC
    0.52
     helical
    0.50
     simulations
    0.50
     polymerized
    0.49
     columnar
    0.48
     ceramic
    0.48
     obtained
    0.47
     Eqs
    0.47
     reformulated
    0.47
     analysis
    0.46
    Activations Density 0.001%

    No Known Activations