© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74497
    Prev
    Next
    INDEX
    Explanations

    news or dates

    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
     with
    -2.48
     this
    -2.30
     if
    -2.23
     first
    -2.14
     when
    -1.91
     ensure
    -1.91
     during
    -1.80
     before
    -1.77
     for
    -1.76
     relentlessly
    -1.71
    POSITIVE LOGITS
    鱨
    1.91
    躂
    1.86
     absolut
    1.84
     ‚
    1.80
    颪
    1.71
     mich
    1.71
    感觉到
    1.70
     típicos
    1.64
     så
    1.63
    ledad
    1.63
    Activations Density 0.009%

    No Known Activations