© 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. 10-GEMMASCOPE-RES-131K
    7. 123660
    Prev
    Next
    INDEX
    Explanations

    "in other words" clarification

    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_10/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
     and
    -2.94
     такая
    -2.42
    </b>
    -2.22
     in
    -2.06
    でも
    -1.91
     los
    -1.68
     такими
    -1.66
     этими
    -1.63
     on
    -1.63
    合う
    -1.63
    POSITIVE LOGITS
     dinosaurio
    2.16
    “
    1.96
    酲
    1.91
    乄
    1.83
    蔟
    1.80
    ércoles
    1.79
    ientras
    1.78
    фера
    1.76
    LEBR
    1.76
     impressão
    1.69
    Activations Density 0.002%

    No Known Activations