© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25717
    Prev
    Next
    INDEX
    Explanations

    variable or type assignment

    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_22/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
     (
    -1.14
     Ví
    -1.12
     Dí
    -1.06
    éricos
    -1.02
     Sé
    -1.02
    ginous
    -1.01
     Tó
    -0.94
    еру
    -0.93
     amé
    -0.93
    кого
    -0.92
    POSITIVE LOGITS
     queste
    1.18
     entgeg
    1.13
     alcune
    1.10
     ploy
    1.08
     inmediatamente
    1.05
     นัก
    1.05
     belangrijk
    1.04
     zwanzig
    1.03
     nachdem
    1.02
    不锈钢
    1.02
    Activations Density 0.063%

    No Known Activations