© 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. 232121
    Prev
    Next
    INDEX
    Explanations

    fixture files

    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
    砳
    0.52
     propriedades
    0.48
    लेरिया
    0.47
     Á
    0.45
     предпочита
    0.45
     dibujos
    0.45
    ᠢ
    0.45
     follicular
    0.44
    णु
    0.43
     খাওয়া
    0.43
    POSITIVE LOGITS
    re
    0.56
    ur
    0.54
    ad
    0.53
    اية
    0.50
    adto
    0.48
    ot
    0.46
    ut
    0.46
    tt
    0.45
    น
    0.45
    niejs
    0.44
    Activations Density 0.000%

    No Known Activations