© 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. 67555
    Prev
    Next
    INDEX
    Explanations

    these photos

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

    chat, settings, summarization

    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
    lett
    0.48
     sof
    0.47
     soda
    0.46
    ,
    0.44
    酒吧
    0.43
     ώστε
    0.43
     shroud
    0.42
     громад
    0.42
     pon
    0.42
    GD
    0.42
    POSITIVE LOGITS
     преми
    0.46
     Mehmet
    0.43
    ediat
    0.43
    
    0.43
    owania
    0.43
    फ्त
    0.42
    மார்க்
    0.42
     연속
    0.42
     মিনি
    0.42
    слежи
    0.42
    Activations Density 0.001%

    No Known Activations