© 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. 218860
    Prev
    Next
    INDEX
    Explanations

    can perform tasks

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

    wings pushing air

    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
    枃
    0.50
    ğe
    0.49
     Ashken
    0.49
     Frédéric
    0.48
     német
    0.48
     portuguesa
    0.46
     norske
    0.46
     рассмотрим
    0.46
     keltiradi
    0.46
     美国
    0.46
    POSITIVE LOGITS
    ｒ
    0.51
     функциона
    0.48
    Particip
    0.46
    каз
    0.44
    ركات
    0.44
    PAR
    0.44
    流
    0.43
    лана
    0.43
    ্ড
    0.43
    Autumn
    0.43
    Activations Density 0.001%

    No Known Activations