© 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. 188927
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    patterns in lists

    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
     consigo
    0.45
    و
    0.44
    وو
    0.44
    临
    0.44
    ו
    0.42
    نا
    0.42
    urança
    0.41
    的两
    0.39
     ዳ
    0.39
     Zustand
    0.38
    POSITIVE LOGITS
    ี้ยว
    0.50
    messer
    0.45
    straction
    0.43
     excitations
    0.42
     त्यावर
    0.42
    蠵
    0.42
    ವೇಂದ್ರ
    0.41
    hess
    0.41
    PerTrial
    0.40
    LLER
    0.40
    Activations Density 0.001%

    No Known Activations