© 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. 193537
    Prev
    Next
    INDEX
    Explanations

    actions, roles, and functions

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

    describing conditions or difficulties

    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
     implementations
    0.50
     potenci
    0.49
    zieć
    0.49
    ن
    0.48
    હ
    0.47
     óta
    0.47
    }-\
    0.47
     있는데요
    0.46
    س
    0.46
     angr
    0.46
    POSITIVE LOGITS
     SupCt
    0.46
     ช่วย
    0.46
    darwin
    0.46
     ແມ່ນ
    0.46
     requested
    0.45
    ary
    0.45
     कार्यकर्ता
    0.45
     ರಲ್ಲಿ
    0.45
    locator
    0.44
     loaned
    0.44
    Activations Density 0.000%

    No Known Activations