© 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. 145348
    Prev
    Next
    INDEX
    Explanations

    time to start

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

    Acquisition Is Initialization

    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
    tidal
    0.52
     )
    0.49
     comprom
    0.49
     Nakam
    0.48
     Configur
    0.48
     admixture
    0.47
     ultraf
    0.47
     (
    0.46
     Мі
    0.46
       
    0.46
    POSITIVE LOGITS
    ې
    0.51
    нинг
    0.51
    க்கும்
    0.50
    에
    0.50
    위에
    0.49
    設備の
    0.49
     chọn
    0.49
     شرطونو
    0.49
    iei
    0.48
     রানী
    0.48
    Activations Density 0.000%

    No Known Activations