© 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. 186681
    Prev
    Next
    INDEX
    Explanations

    making choices and obtaining

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

    exploring pros and cons

    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
     š
    0.46
     افز
    0.45
     کال
    0.44
     eel
    0.44
     절
    0.44
     pcs
    0.43
    !=
    0.43
     ethereum
    0.43
     instal
    0.43
     흔
    0.43
    POSITIVE LOGITS
     समक्ष
    0.44
    ক্ষে
    0.43
    latin
    0.43
    icularly
    0.43
    acies
    0.42
    aprendizaje
    0.42
    方面
    0.41
    geographic
    0.41
    னிய
    0.41
    ಲ್ಲು
    0.41
    Activations Density 0.000%

    No Known Activations