© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66548
    Prev
    Next
    INDEX
    Explanations

    time ranges and specific times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -2.34
    沇
    -2.31
    と
    -2.28
    ).”
    -2.27
    aval
    -2.17
     deberá
    -2.14
     sway
    -2.14
    )?
    -2.13
    攆
    -2.13
    
    -2.09
    POSITIVE LOGITS
    ’
    2.86
    饜
    2.45
    ⡪
    2.25
    媜
    2.16
     padx
    2.13
    寕
    2.06
    بة
    2.03
    〮
    2.03
     SqlParameter
    2.02
     veren
    2.02
    Activations Density 0.001%

    No Known Activations