© 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. 85500
    Prev
    Next
    INDEX
    Explanations

    past actions and events

    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
     from
    -2.02
     its
    -1.66
    Its
    -1.31
    ڡ
    -1.31
     spazi
    -1.30
     which
    -1.27
     ње
    -1.27
    decoração
    -1.23
    hộp
    -1.23
    There
    -1.23
    POSITIVE LOGITS
     we
    1.57
    probably
    1.41
    isks
    1.31
     I
    1.30
     kritik
    1.26
     milieux
    1.24
    during
    1.23
    creates
    1.21
    −/−
    1.20
    really
    1.20
    Activations Density 0.105%

    No Known Activations