© 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. 58560
    Prev
    Next
    INDEX
    Explanations

    reporting financial results and incidents

    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
     what
    -1.56
     號
    -1.54
    It
    -1.43
     meski
    -1.42
    2
    -1.41
    Also
    -1.41
    F
    -1.41
    6
    -1.39
     meskipun
    -1.37
     jenen
    -1.36
    POSITIVE LOGITS
     success
    1.54
    "
    1.53
    coffret
    1.48
    pochette
    1.45
     zanahoria
    1.44
    bui
    1.41
    bonsoir
    1.38
     nových
    1.38
     is
    1.36
     fotó
    1.36
    Activations Density 0.039%

    No Known Activations