© 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. 13510
    Prev
    Next
    INDEX
    Explanations

    counting words like two, both

    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
    cension
    -0.82
     certain
    -0.79
    ppling
    -0.78
    roring
    -0.75
    -0.74
     many
    -0.73
     (!$
    -0.71
    }`;
    -0.71
     "]";
    -0.71
    larına
    -0.71
    POSITIVE LOGITS
     two
    1.88
     both
    1.76
     beiden
    1.34
     både
    1.32
     два
    1.31
     두
    1.30
    Both
    1.30
    both
    1.26
    两个
    1.24
     двумя
    1.23
    Activations Density 0.088%

    No Known Activations