© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4943
    Prev
    Next
    INDEX
    Explanations

    while, to, when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esenciales
    0.14
    》。
    0.13
     (-)
    0.13
    aniyati
    0.13
     Allies
    0.13
     ذریع
    0.13
     calorías
    0.13
    。
    0.13
     ہیں۔
    0.13
     {}".
    0.13
    POSITIVE LOGITS
    pping
    0.20
    с
    0.19
    cknowled
    0.18
    at
    0.18
    swering
    0.18
    cing
    0.17
    un
    0.16
     the
    0.16
    ostante
    0.16
    pped
    0.16
    Activations Density 0.295%

    No Known Activations