© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60556
    Prev
    Next
    INDEX
    Explanations

    documentation parameters and types

    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
     ARISING
    -1.69
    indicate
    -1.56
    quite
    -1.55
     soi
    -1.53
    :
    -1.52
    .")]
    -1.49
     huiles
    -1.45
     refroid
    -1.42
     célèbre
    -1.41
     graines
    -1.40
    POSITIVE LOGITS
     for
    2.64
     to
    2.09
     which
    2.08
     of
    2.05
     that
    2.05
     or
    1.98
     where
    1.91
     should
    1.91
     with
    1.77
    خطيط
    1.52
    Activations Density 0.056%

    No Known Activations