© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64889
    Prev
    Next
    INDEX
    Explanations

    dictionaries, programming, code

    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_all/layer_41_width_262k_l0_big
    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
    腦
    0.45
    zien
    0.44
     kwe
    0.43
     அழ
    0.43
     enriqu
    0.42
     om
    0.41
     кора
    0.40
     zhī
    0.40
     zien
    0.39
     아니
    0.39
    POSITIVE LOGITS
    含
    0.40
    高于
    0.38
     ileri
    0.38
     Micah
    0.37
     Saturday
    0.36
     把
    0.36
     monument
    0.35
     Admit
    0.35
    StatusBadRequest
    0.35
     protected
    0.35
    Activations Density 0.563%

    No Known Activations