© 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. 218562
    Prev
    Next
    INDEX
    Explanations

    paper slips counted and compared

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

    question mark, closing parenthesis, asterisk

    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
     Como
    0.50
     Kaise
    0.48
    你會
    0.47
     Prepar
    0.46
     工作
    0.46
    ಾಂಶ
    0.46
     會
    0.46
     Chaque
    0.45
     Hanya
    0.45
     promete
    0.45
    POSITIVE LOGITS
    ج
    0.45
     esim
    0.44
    nap
    0.43
    vZ
    0.43
    ণ্ঠে
    0.42
    rys
    0.42
    ford
    0.42
    LIS
    0.42
    an
    0.41
    aj
    0.41
    Activations Density 0.000%

    No Known Activations