© 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. 34251
    Prev
    Next
    INDEX
    Explanations

    the house, service, be established

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

    delivery issue

    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
     KMS
    0.48
    kits
    0.45
    2
    0.44
     Ako
    0.44
     turut
    0.44
        
    0.43
     kina
    0.43
    claves
    0.43
     Supplier
    0.43
    <u>
    0.42
    POSITIVE LOGITS
     преобразова
    0.58
     ወይም
    0.55
     имму
    0.53
    劶
    0.51
     энерги
    0.50
     великолеп
    0.50
     присутствует
    0.50
     или
    0.49
     дра
    0.47
     аккумулятор
    0.47
    Activations Density 0.000%

    No Known Activations