© 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. 12728
    Prev
    Next
    INDEX
    Explanations

    state or relation

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

    explaining how to

    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
    j
    0.64
    k
    0.64
    c
    0.62
    f
    0.62
    y
    0.60
    W
    0.59
    l
    0.58
    T
    0.58
    g
    0.57
    J
    0.57
    POSITIVE LOGITS
     কখনো
    0.56
     anvä
    0.55
     ইতিমধ্যে
    0.52
     зміню
    0.50
     ঘট
    0.50
     используется
    0.50
    ப்பாடு
    0.50
     utilizzato
    0.50
     dunno
    0.50
     används
    0.50
    Activations Density 0.000%

    No Known Activations