© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74865
    Prev
    Next
    INDEX
    Explanations

    fired power boilers

    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
     the
    -1.42
     filósofo
    -1.38
    üğü
    -1.37
     entrando
    -1.35
     ontdek
    -1.35
     verkla
    -1.28
    »،
    -1.27
     wich
    -1.27
     fermés
    -1.27
    Dí
    -1.26
    POSITIVE LOGITS
    s
    1.51
    蓠
    1.44
     same
    1.41
    ｙ
    1.38
    ScopeManager
    1.38
    vec
    1.35
     未
    1.35
     人
    1.33
    YOUR
    1.30
    şört
    1.30
    Activations Density 0.006%

    No Known Activations