© 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. 157591
    Prev
    Next
    INDEX
    Explanations

    types ofaccessible onlinerepresented onMPH analog

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

    Elon Musk, assistant

    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
    στο
    0.50
     NCBI
    0.49
     Pubmed
    0.48
     antibiot
    0.48
    楝
    0.47
    ಕ್ಕು
    0.46
     preoc
    0.46
     strcat
    0.45
     Virology
    0.44
    ంబేద్కర్
    0.44
    POSITIVE LOGITS
    ek
    0.57
    ă
    0.50
    6
    0.49
    uyor
    0.49
    iler
    0.49
    5
    0.48
    alah
    0.47
    hte
    0.47
    ioneer
    0.46
    ăș
    0.46
    Activations Density 0.000%

    No Known Activations