© 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. 34-GEMMASCOPE-RES-131K
    7. 77676
    Prev
    Next
    INDEX
    Explanations

    citations and delimitings

    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_34/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
    -1.82
     and
    -1.73
     this
    -1.59
     ostensibly
    -1.56
     some
    -1.52
     from
    -1.50
     allows
    -1.48
     at
    -1.46
     gives
    -1.41
     knows
    -1.41
    POSITIVE LOGITS
     Dinas
    1.66
     terminer
    1.57
    twenty
    1.56
     faciliter
    1.55
     alluring
    1.44
     masterful
    1.42
     colorés
    1.38
    鼍
    1.37
     magnific
    1.36
     unsettling
    1.36
    Activations Density 0.141%

    No Known Activations