© 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. 120040
    Prev
    Next
    INDEX
    Explanations

    chipset integrated drivers

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

    past contexts and information

    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
    Manip
    0.47
    मेन
    0.46
    ن
    0.46
    㸽
    0.45
    րան
    0.44
    نا
    0.43
    ه
    0.43
    argu
    0.43
    თ
    0.43
    顶级
    0.42
    POSITIVE LOGITS
    नलिखित
    0.50
     ovaries
    0.50
     unfolds
    0.48
    olip
    0.48
     crossbody
    0.45
     croissants
    0.45
     abut
    0.44
     curvatures
    0.44
     endpoints
    0.44
     unbound
    0.44
    Activations Density 0.000%

    No Known Activations