© 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. 134226
    Prev
    Next
    INDEX
    Explanations

    necessary to

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

    types of descriptions

    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
    sky
    0.50
    ς
    0.46
    かる
    0.46
    unction
    0.45
    raction
    0.44
    eris
    0.44
    specific
    0.44
    pecific
    0.43
     combinar
    0.43
    tti
    0.43
    POSITIVE LOGITS
     представление
    0.51
     asker
    0.49
     уйнау
    0.46
    PhotoButton
    0.43
     мнение
    0.43
    হাত
    0.43
    闿
    0.42
     grafik
    0.42
    জাম
    0.42
     заявления
    0.42
    Activations Density 0.001%

    No Known Activations