© 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. 24906
    Prev
    Next
    INDEX
    Explanations

    book but, closely associated

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

    ventricular tachycardia

    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
     Responsible
    0.41
    甫
    0.40
    への
    0.40
     prema
    0.39
     selaku
    0.38
     ostensibly
    0.38
     già
    0.37
     protiv
    0.37
     場
    0.37
     ageing
    0.36
    POSITIVE LOGITS
     אך
    0.58
     પરંતુ
    0.50
    tahun
    0.50
     ਨਹੀਂ
    0.49
     lakini
    0.47
    买了
    0.46
    锃
    0.46
    incinn
    0.46
    zechos
    0.46
     चूक
    0.46
    Activations Density 0.000%

    No Known Activations