© 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. 21188
    Prev
    Next
    INDEX
    Explanations

    down on / off on

    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
    jekk
    -1.55
     eletrônico
    -1.34
    ING
    -1.22
    回来了
    -1.22
     MADRID
    -1.21
    сті
    -1.20
     móvel
    -1.20
     источники
    -1.20
    ju
    -1.20
    where
    -1.19
    POSITIVE LOGITS
     for
    1.76
    ganggu
    1.44
     from
    1.41
     against
    1.38
    男人
    1.35
     siitä
    1.29
     Again
    1.26
     overzicht
    1.25
     sebuah
    1.24
    vky
    1.22
    Activations Density 0.083%

    No Known Activations