© 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. 165876
    Prev
    Next
    INDEX
    Explanations

    locations and distances

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

    specific document 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
     predic
    0.51
     probe
    0.50
     (
    0.48
     oport
    0.45
     day
    0.45
     resin
    0.45
    ta
    0.44
     regiment
    0.44
     relevante
    0.44
    ↵
    0.43
    POSITIVE LOGITS
     паліты
    0.56
     Buildings
    0.49
     храм
    0.49
    inesis
    0.49
    观众
    0.49
    த்திலிருந்து
    0.49
    ्यानंतर
    0.48
    ijnlijk
    0.48
    ۳
    0.48
    ूर्ति
    0.48
    Activations Density 0.000%

    No Known Activations