© 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. 152381
    Prev
    Next
    INDEX
    Explanations

    planning and assumptions

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

    responsible for search

    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
    änger
    0.48
     পুঁ
    0.45
     चले
    0.45
     dispersed
    0.44
    𝐞
    0.44
     Forschung
    0.44
    regated
    0.43
    assembled
    0.43
    embry
    0.43
     Wohnung
    0.43
    POSITIVE LOGITS
    一家
    0.52
    Uno
    0.51
     necessaria
    0.49
     immobilier
    0.49
    ಲ್
    0.48
    شو
    0.47
    おしゃれ
    0.47
    Ở
    0.47
     importanti
    0.46
    ཌ
    0.46
    Activations Density 0.001%

    No Known Activations