© 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. 127690
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
     offerte
    -1.69
    cuando
    -1.64
    ٣
    -1.58
    ٨
    -1.58
    ïque
    -1.57
     urgente
    -1.57
    aient
    -1.56
     فقط
    -1.55
     wasnt
    -1.53
     fortfarande
    -1.53
    POSITIVE LOGITS
     so
    2.47
     and
    2.16
     not
    2.03
     well
    1.98
     this
    1.95
     our
    1.92
     in
    1.91
     full
    1.87
     for
    1.84
     use
    1.82
    Activations Density 0.214%

    No Known Activations