© 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. 218598
    Prev
    Next
    INDEX
    Explanations

    phrases ending sentences or clauses

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

    lists and explanations

    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
     COMP
    0.44
     parts
    0.44
    lcc
    0.44
    вершен
    0.41
     buts
    0.41
     buddh
    0.40
     large
    0.39
    t
    0.39
    ປະກອບ
    0.39
    gk
    0.39
    POSITIVE LOGITS
     शनिवार
    0.46
    AlertType
    0.45
    dirty
    0.43
     исправ
    0.43
    notify
    0.43
     brindar
    0.42
    astype
    0.42
    ോഷ്യ
    0.41
     रिले
    0.41
    实例
    0.41
    Activations Density 0.001%

    No Known Activations