© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71395
    Prev
    Next
    INDEX
    Explanations

    Borel set, Aquarius

    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
    You
    -2.69
    If
    -2.69
    [
    -2.44
    In
    -2.44
    🫘
    -2.36
    =
    -2.31
    ]
    -2.28
    на
    -2.28
    櫚
    -2.27
    而在
    -2.20
    POSITIVE LOGITS
    茘
    2.59
    珝
    2.36
    琤
    2.36
    釭
    2.31
     interrump
    2.28
    枰
    2.28
     aislados
    2.27
     atentos
    2.25
    戩
    2.25
    鷸
    2.23
    Activations Density 0.025%

    No Known Activations