© 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. 129096
    Prev
    Next
    INDEX
    Explanations

    data types and structures

    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
     {
    -1.27
    s
    -1.20
     with
    -1.12
     ребен
    -1.11
     gustaba
    -1.10
    `:
    -1.09
     pese
    -1.07
    ',
    -1.06
     at
    -1.06
     sueño
    -1.04
    POSITIVE LOGITS
    \&
    1.35
     \&
    1.35
    щихся
    1.23
     μέχρι
    1.20
    NDICE
    1.20
    
    1.18
     thì
    1.18
    sistency
    1.15
     kemudian
    1.09
     Sentence
    1.09
    Activations Density 0.059%

    No Known Activations