© 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. 70171
    Prev
    Next
    INDEX
    Explanations

    website, Easter, insurance, gap

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

    supports many languages

    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
     in
    0.62
     ,
    0.56
    ine
    0.54
    G
    0.54
    organ
    0.53
     articular
    0.50
     ফ
    0.50
     F
    0.49
     of
    0.49
    In
    0.49
    POSITIVE LOGITS
    aniyati
    0.50
    ipedi
    0.50
    ፴
    0.49
    rition
    0.48
    뷁
    0.47
    კის
    0.46
    што
    0.46
    孀
    0.46
    డు
    0.45
     cnv
    0.45
    Activations Density 0.001%

    No Known Activations