© 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. 73447
    Prev
    Next
    INDEX
    Explanations

    variety of options

    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
     there
    -1.66
     décédé
    -1.62
     it
    -1.49
    allows
    -1.44
    apore
    -1.40
     Instead
    -1.36
    icating
    -1.36
    There
    -1.34
    visiae
    -1.34
     actuelle
    -1.31
    POSITIVE LOGITS
     of
    2.38
    </em>
    1.81
    \&
    1.35
     magasiner
    1.34
     brune
    1.32
     pittores
    1.27
     ovale
    1.26
     torsdag
    1.25
    ']=$
    1.24
     bidra
    1.24
    Activations Density 0.038%

    No Known Activations