© 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. 40917
    Prev
    Next
    INDEX
    Explanations

    same day and programming

    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
     he
    -2.88
     '
    -2.63
     of
    -2.52
     \
    -2.27
    <bos>
    -2.11
     
    -2.08
    ]
    -2.00
     is
    -1.99
    ,"
    -1.97
    简称
    -1.97
    POSITIVE LOGITS
    焢
    2.84
    ܜ
    2.52
     lainnya
    2.44
    卨
    2.28
    綃
    2.28
    when
    2.25
    鏵
    2.20
    When
    2.08
    same
    2.06
     給
    2.06
    Activations Density 0.008%

    No Known Activations