© 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. 136485
    Prev
    Next
    INDEX
    Explanations

    company names and people

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

    attribute access like

    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
    “)
    0.45
    ”).
    0.45
    ”)
    0.42
    yf
    0.42
    )،
    0.42
     وړ
    0.42
    ي
    0.42
     कीट
    0.41
     )।
    0.41
    糞
    0.41
    POSITIVE LOGITS
    년부터
    0.47
    +(\
    0.44
     Cálculo
    0.44
    ที่คุณ
    0.41
     GetComponent
    0.40
    ้าง
    0.39
     generates
    0.39
     governs
    0.38
    úcar
    0.38
     sucedido
    0.38
    Activations Density 0.006%

    No Known Activations