© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95386
    Prev
    Next
    INDEX
    Explanations

    phrase beginnings

    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
    ilumin
    -1.13
     moletom
    -1.08
    kug
    -1.03
     sereia
    -1.03
    consumo
    -1.03
     linho
    -1.01
    ipient
    -1.00
    zmm
    -1.00
     boneca
    -1.00
     contesto
    -0.98
    POSITIVE LOGITS
     with
    1.05
    }$
    1.01
    너
    1.00
     ३
    0.94
    rr
    0.94
    psilon
    0.94
    AM
    0.93
    is
    0.93
     berkomunikasi
    0.92
    ometry
    0.90
    Activations Density 0.012%

    No Known Activations