© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64956
    Prev
    Next
    INDEX
    Explanations

    either...or structure

    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
     any
    -1.44
     qualsiasi
    -1.20
    Система
    -1.13
    PENDAHULUAN
    -1.13
     both
    -1.13
    ANY
    -1.10
     BEAUTIFUL
    -1.10
    Banyak
    -1.09
     concret
    -1.07
    Cinta
    -1.06
    POSITIVE LOGITS
     are
    1.80
     were
    1.40
     have
    1.37
     has
    1.16
     their
    1.11
     directamente
    1.08
     involved
    1.08
     had
    1.03
     Either
    1.00
    มาณ
    0.97
    Activations Density 0.059%

    No Known Activations