© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 289
    Prev
    Next
    INDEX
    Explanations

    what starts questions

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

    what

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695

    question words

    np_max-act · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
     estejam
    0.25
     zowel
    0.24
     mesmas
    0.24
     stets
    0.24
     있지만
    0.23
     jedynie
    0.23
     देखील
    0.23
    雖
    0.23
     虽然
    0.23
     zwar
    0.22
    POSITIVE LOGITS
    ?
    0.37
    ？
    0.33
    难道
    0.33
    はどう
    0.32
    ?";
    0.32
    ?“
    0.32
     réellement
    0.32
    …?
    0.32
    What
    0.31
     is
    0.31
    Activations Density 1.752%

    No Known Activations