© 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. 248022
    Prev
    Next
    INDEX
    Explanations

    historical and current trends

    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
     प्लेयर्स
    0.50
    </h2>
    0.48
    sType
    0.48
    <0x0D>
    0.44
     可能
    0.44
    Orders
    0.42
    iasa
    0.41
     号
    0.41
    ='',
    0.40
    NewGuid
    0.40
    POSITIVE LOGITS
     helfen
    0.54
     freund
    0.52
     bestät
    0.50
     proté
    0.49
     svart
    0.49
     bestätigt
    0.48
     helpen
    0.47
     forskj
    0.47
     Anzeigen
    0.46
    fahrt
    0.46
    Activations Density 0.001%

    No Known Activations