© 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. 49282
    Prev
    Next
    INDEX
    Explanations

    after compression

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

    bursa sacs

    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
     couleurs
    0.47
     lieux
    0.46
     dataGridView
    0.44
     та
    0.44
    égio
    0.44
     இறுதியில்
    0.44
    ዉ
    0.44
     couleur
    0.43
     getType
    0.43
     સૌથી
    0.42
    POSITIVE LOGITS
    埸
    0.49
    EDS
    0.47
     Gorgeous
    0.47
    唛
    0.47
    lel
    0.46
     Chrome
    0.46
     Isolated
    0.46
     Sausage
    0.45
     Trainers
    0.45
     Fallon
    0.44
    Activations Density 0.000%

    No Known Activations