© 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. 27734
    Prev
    Next
    INDEX
    Explanations

    Found: 0

    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
    なんだけど
    -1.12
     enamorado
    -1.05
     серый
    -1.04
     unusual
    -1.04
     democrática
    -1.03
     podob
    -1.02
    なのかな
    -1.01
    ₿
    -1.01
    Menurut
    -1.00
     satisfecho
    -1.00
    POSITIVE LOGITS
    still
    1.35
     Atención
    1.17
    踴
    1.15
     ilustrasi
    1.13
    蝼
    1.12
     restaurante
    1.11
     thoſe
    1.08
     trium
    1.08
    řej
    1.05
     Wartawan
    1.05
    Activations Density 0.018%

    No Known Activations