© 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. 239102
    Prev
    Next
    INDEX
    Explanations

    competitive outcomes and events

    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
    𝚙
    0.59
    adn
    0.51
     министер
    0.51
    𝚖
    0.50
     کارکن
    0.50
    𝙼
    0.49
    𝚝
    0.48
    robespierre
    0.48
    adl
    0.48
    adım
    0.47
    POSITIVE LOGITS
     supposedly
    0.57
     helmet
    0.54
     porous
    0.51
     camshaft
    0.49
     immigrant
    0.49
     firearms
    0.49
     heterogeneous
    0.48
     terminology
    0.48
     a
    0.47
     histo
    0.47
    Activations Density 0.000%

    No Known Activations