© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11101
    Prev
    Next
    INDEX
    Explanations

    street names and abbreviations

    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
     Some
    -1.10
    H
    -1.09
    _
    -1.06
    J
    -1.05
    L
    -1.05
     some
    -1.00
    '
    -1.00
     glaubt
    -0.97
    T
    -0.97
    M
    -0.94
    POSITIVE LOGITS
     madres
    1.13
    𓁹
    1.09
     män
    1.09
     japones
    1.07
     espacial
    1.05
    MÁS
    1.05
    tarte
    1.05
     informaci
    1.05
     wohnung
    1.03
     anunci
    1.02
    Activations Density 0.019%

    No Known Activations