© 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. 113253
    Prev
    Next
    INDEX
    Explanations

    holiday greetings and birthdays

    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
     during
    -1.95
     but
    -1.87
    ).
    -1.75
    婚礼
    -1.66
     at
    -1.66
     using
    -1.66
     when
    -1.58
     such
    -1.55
     about
    -1.51
    ByVersion
    -1.44
    POSITIVE LOGITS
    .
    1.67
     pratiquer
    1.66
     Probl
    1.58
     provenant
    1.50
     prouver
    1.45
    𝐌
    1.44
    哐
    1.42
     patienter
    1.41
     foremost
    1.38
     kimdir
    1.38
    Activations Density 0.004%

    No Known Activations