© 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. 22-GEMMASCOPE-RES-131K
    7. 14025
    Prev
    Next
    INDEX
    Explanations

    numbered lists or equations

    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
     durabilidad
    -1.27
    久し
    -1.24
    すっ
    -1.23
    に入れる
    -1.22
     zwykle
    -1.21
     fiabilidad
    -1.20
    色々と
    -1.20
    さぁ
    -1.17
     preferencias
    -1.16
    tratamiento
    -1.16
    POSITIVE LOGITS
     because
    1.13
     only
    1.13
     by
    1.06
     if
    1.05
    jardin
    1.04
    外部連結
    1.02
     now
    1.02
    avajillas
    1.02
     radikal
    1.00
    because
    1.00
    Activations Density 0.011%

    No Known Activations