© 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. 240898
    Prev
    Next
    INDEX
    Explanations

    commercial vehicle

    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
     allocated
    0.47
     metropolitan
    0.47
     trunk
    0.47
     contextual
    0.44
     standardization
    0.43
    ъ
    0.43
     inherited
    0.43
     receive
    0.43
     concurrency
    0.43
     tokenize
    0.42
    POSITIVE LOGITS
     odlič
    0.52
    она
    0.50
     ஏற்பட்டது
    0.50
    пре
    0.50
    いろいろ
    0.46
     कुलपति
    0.46
    Ahmed
    0.46
    ἦ
    0.46
     był
    0.45
     его
    0.45
    Activations Density 0.001%

    No Known Activations