© 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. 113329
    Prev
    Next
    INDEX
    Explanations

    right place

    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
    ,
    -1.55
     my
    -1.52
     encantador
    -1.51
     such
    -1.48
    那么
    -1.35
     But
    -1.33
     vraiment
    -1.30
     fazendo
    -1.29
    y
    -1.29
     you
    -1.28
    POSITIVE LOGITS
     until
    1.74
    悒
    1.50
     confirms
    1.45
    缟
    1.41
    DIPSETTING
    1.39
     ieri
    1.39
    
    1.36
     almeno
    1.30
    umesc
    1.30
     exorbit
    1.29
    Activations Density 0.019%

    No Known Activations