© 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. 48442
    Prev
    Next
    INDEX
    Explanations

    action followed by consequence

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

    end of sentence or phrase

    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
    דה
    0.47
    Zoo
    0.45
    Source
    0.45
    Ola
    0.44
    Uttar
    0.44
    DEFINE
    0.43
    
    0.43
    CURRENT
    0.43
    주
    0.42
    Cert
    0.42
    POSITIVE LOGITS
    ប្រ
    0.49
     宮
    0.47
    投げ
    0.47
     উদ্বোধন
    0.44
     যথার্থ
    0.44
     radially
    0.44
    ্লেখ
    0.43
    inky
    0.43
    िनेशन
    0.43
    tsó
    0.43
    Activations Density 0.000%

    No Known Activations