© 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. 4480
    Prev
    Next
    INDEX
    Explanations

    programming variables and declaration

    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
     محس
    0.42
    of
    0.41
     ‘
    0.39
    getContent
    0.39
    勸
    0.39
    O
    0.39
    usage
    0.38
    E
    0.38
    get
    0.37
     “
    0.37
    POSITIVE LOGITS
     وړاندوینه
    0.46
    ковые
    0.44
     비슷
    0.43
     doped
    0.42
    ILITIES
    0.40
     പിന്നീ
    0.40
    ەیە
    0.40
     kinases
    0.40
     같다
    0.40
    ក្រោយ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.