© 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. 186103
    Prev
    Next
    INDEX
    Explanations

    Coupon codes and discounts

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

    moderate, difficult, easy

    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
     CH
    0.48
     radioButton
    0.43
     GIVE
    0.43
     Ч
    0.42
     repurchase
    0.41
     ICH
    0.40
     FIRST
    0.40
    楚
    0.39
     firstName
    0.38
     ys
    0.38
    POSITIVE LOGITS
    ülü
    0.54
    𝓽
    0.52
     candidats
    0.50
    limegreen
    0.50
    ExposureTime
    0.50
     candidatos
    0.49
    Macrophages
    0.49
    guna
    0.49
     sitzt
    0.49
    قیم
    0.48
    Activations Density 0.001%

    No Known Activations