© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32099
    Prev
    Next
    INDEX
    Explanations

    XML Schema and badges

    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_34/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
    אח
    -0.81
    österreich
    -0.69
    Exhibit
    -0.68
    Expansion
    -0.68
    樓
    -0.67
     wideo
    -0.67
    ナイト
    -0.67
     monit
    -0.66
    expiry
    -0.66
    楽曲
    -0.66
    POSITIVE LOGITS
    Bless
    0.84
    тке
    0.80
    CLICK
    0.77
    Forgive
    0.74
    click
    0.72
     MCA
    0.71
    flick
    0.71
     Quint
    0.71
     Calam
    0.70
     Olin
    0.70
    Activations Density 0.027%

    No Known Activations