© 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. 221975
    Prev
    Next
    INDEX
    Explanations

    sales and events

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

    GDP size, cotton canvas, Bassington-Smith

    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
     Habitat
    0.50
     Montag
    0.49
    雲
    0.49
     Tuesday
    0.47
     sectoral
    0.47
     address
    0.46
    不足
    0.46
     Joe
    0.46
     Moh
    0.46
     RAN
    0.45
    POSITIVE LOGITS
    EnglishMarks
    0.56
    dimg
    0.55
    DLJ
    0.51
    nummer
    0.50
    Beyblade
    0.50
    edo
    0.47
    <0x15>
    0.46
    নির্দিষ্ট
    0.46
     करेक्ट
    0.46
    Carta
    0.45
    Activations Density 0.001%

    No Known Activations