© 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. 239419
    Prev
    Next
    INDEX
    Explanations

    daily National Survey

    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
    inite
    0.51
     ziem
    0.49
    laden
    0.49
    descriptions
    0.48
    ه
    0.48
    nač
    0.47
     soruml
    0.46
    n
    0.46
    yawa
    0.46
    rahman
    0.46
    POSITIVE LOGITS
     Hunter
    0.44
     रखने
    0.43
    ள்ளதாக
    0.43
    䏍
    0.43
    釟
    0.43
     बचाव
    0.43
    রাট
    0.43
     потре
    0.42
     Comptroller
    0.42
     поможет
    0.42
    Activations Density 0.001%

    No Known Activations