© 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. 73792
    Prev
    Next
    INDEX
    Explanations

    sponsors and sponsorship

    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
    1
    -2.33
    There
    -2.27
    )
    -2.22
    (
    -2.22
     all
    -2.20
     Definitely
    -2.14
     Going
    -2.11
    /
    -2.08
     Probably
    -2.06
    4
    -2.03
    POSITIVE LOGITS
    饪
    2.41
    鈈
    2.19
     グラン
    2.09
    鱨
    2.08
     alſo
    2.05
     parachoque
    2.05
     zoude
    2.03
    挣
    2.02
    為に
    2.00
     装修
    1.98
    Activations Density 0.004%

    No Known Activations