© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105375
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or counties

    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
     founded
    -1.20
    ECM
    -1.17
    ⅴ
    -1.14
     timmar
    -1.13
     Permits
    -1.08
    ündung
    -1.07
     each
    -1.06
    prende
    -1.05
    ziału
    -1.05
     spawns
    -1.04
    POSITIVE LOGITS
    )"
    1.20
     claus
    1.13
     ilgi
    1.09
     koy
    1.07
     Empres
    1.07
    setMinimum
    1.06
    podob
    1.04
     +
    1.03
    ように
    1.02
    chlor
    1.02
    Activations Density 0.332%

    No Known Activations