© 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. 67352
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    interconnected systems and their difficulties

    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
    轲
    0.45
    return
    0.44
     refreshing
    0.43
    immer
    0.42
    panelMenuList
    0.42
     Mono
    0.42
     Supervision
    0.42
    瑩
    0.42
    град
    0.41
    、
    0.41
    POSITIVE LOGITS
     señal
    0.52
     ايضا
    0.51
     redshifts
    0.50
    発
    0.50
     variété
    0.48
     parejas
    0.48
     noirâtres
    0.47
    ்ட்
    0.47
    JG
    0.47
    ualmente
    0.46
    Activations Density 0.001%

    No Known Activations