© 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. 196460
    Prev
    Next
    INDEX
    Explanations

    institutional or official phrasing

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

    analysis of documents

    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
     certification
    0.49
    <0x94>
    0.48
    मिति
    0.48
    Downloads
    0.46
    ம்
    0.46
     REIT
    0.45
    Issued
    0.44
     RECE
    0.43
     banknote
    0.43
    ം
    0.43
    POSITIVE LOGITS
     우리가
    0.59
     위해서는
    0.52
    zelf
    0.48
     మనం
    0.46
     നമു
    0.46
     우리는
    0.45
     Rossa
    0.45
     داله
    0.45
     Flughafen
    0.45
    setMax
    0.45
    Activations Density 0.000%

    No Known Activations