© 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. 231716
    Prev
    Next
    INDEX
    Explanations

    force all, like bing

    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
     niệm
    0.49
     kutoka
    0.43
    രിച്ചു
    0.43
     hton
    0.42
     relayed
    0.41
     nonlocal
    0.41
    ޟ
    0.41
    ლა
    0.40
     난
    0.40
     bei
    0.39
    POSITIVE LOGITS
    UL
    0.53
    Jest
    0.46
    excludeFolder
    0.45
    '
    0.44
     FMC
    0.42
    们
    0.42
     প্রতিষ্ঠান
    0.41
    SuppressWarnings
    0.41
    दिग्ध
    0.41
     इकाई
    0.41
    Activations Density 0.001%

    No Known Activations