© 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. 228577
    Prev
    Next
    INDEX
    Explanations

    risk or shortage

    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
     Recogn
    0.48
    Survivor
    0.48
     Survivor
    0.47
     ভুগ
    0.47
    生
    0.46
     Survive
    0.45
    的时
    0.44
    that
    0.43
     Drink
    0.43
     জিত
    0.43
    POSITIVE LOGITS
    iranje
    0.50
    ows
    0.47
     qilish
    0.46
     bols
    0.46
     scur
    0.46
     kekurangan
    0.46
    anya
    0.46
    unos
    0.45
    ˗
    0.45
     याच
    0.45
    Activations Density 0.002%

    No Known Activations