© 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. 62480
    Prev
    Next
    INDEX
    Explanations

    highways and rest stops

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

    listing categories

    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
     प्रमाणात
    0.47
    乆
    0.46
    不会
    0.45
    蓍
    0.45
    露
    0.44
     ভোটার
    0.44
    笫
    0.44
     nooit
    0.44
    论
    0.43
    也不会
    0.42
    POSITIVE LOGITS
     getaway
    0.44
    ferred
    0.39
    centric
    0.38
    וי
    0.38
     cowardly
    0.37
     hike
    0.37
    šev
    0.37
    MTV
    0.37
     do
    0.37
    summon
    0.36
    Activations Density 0.000%

    No Known Activations