© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101932
    Prev
    Next
    INDEX
    Explanations

    partnering or teamed up

    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
    htiö
    -1.29
    ()==
    -1.27
    idopsis
    -1.26
     falda
    -1.24
     militaire
    -1.24
     itself
    -1.24
     trochę
    -1.23
    **/
    
    -1.22
     gouttes
    -1.20
    
    -1.20
    POSITIVE LOGITS
     are
    1.35
    ைகள்
    1.22
     from
    1.20
    蒞
    1.20
     that
    1.19
     This
    1.19
     other
    1.18
     Ärz
    1.14
    jasa
    1.13
     more
    1.10
    Activations Density 0.024%

    No Known Activations