© 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. 132858
    Prev
    Next
    INDEX
    Explanations

    days and lists of friends

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

    oobabooga WebUI, Org, account reset

    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
    at
    0.54
    1
    0.50
     silica
    0.50
    8
    0.46
    7
    0.46
    नाची
    0.46
     SMART
    0.45
     দলকে
    0.44
    ना
    0.44
    xFF
    0.44
    POSITIVE LOGITS
     коле
    0.49
    ൂര്‍
    0.47
     పిల్ల
    0.46
    excludeFolder
    0.45
    Guitar
    0.45
    卄
    0.45
     знай
    0.44
    吘
    0.44
     باقي
    0.44
     фаса
    0.44
    Activations Density 0.002%

    No Known Activations