© 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. 240489
    Prev
    Next
    INDEX
    Explanations

    screens and displays

    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
    aile
    0.52
    pectral
    0.49
    ian
    0.47
    ophag
    0.47
    spectral
    0.47
    嚥
    0.47
    spectrum
    0.44
    ệm
    0.44
    enson
    0.44
    irit
    0.44
    POSITIVE LOGITS
     cend
    0.51
     ity
    0.50
     cinder
    0.49
     ital
    0.48
    🧑
    0.48
     {},
    0.47
     Jimi
    0.47
     buzz
    0.47
     ő
    0.46
     Zayed
    0.46
    Activations Density 0.003%

    No Known Activations