© 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. 63876
    Prev
    Next
    INDEX
    Explanations

    introduces verb

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

    potential disruptions and analogy

    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
    癤
    0.51
    ugg
    0.48
    ;
    0.46
     Chinatown
    0.44
    geschossiges
    0.44
    Comment
    0.43
     Precious
    0.43
     Hollywood
    0.42
     Bondi
    0.42
    ield
    0.42
    POSITIVE LOGITS
     ".$
    0.56
    dh
    0.49
     maintains
    0.49
     yoki
    0.47
     provides
    0.46
     fornisce
    0.46
     muere
    0.46
     monitors
    0.45
     alleges
    0.45
     ensures
    0.45
    Activations Density 0.000%

    No Known Activations