© 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. 34-GEMMASCOPE-RES-131K
    7. 23841
    Prev
    Next
    INDEX
    Explanations

    free software licenses and permissions

    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
     Eternal
    -0.71
     хо
    -0.71
    踹
    -0.70
    ={<
    -0.69
     Niro
    -0.69
    make
    -0.68
    esteem
    -0.68
     horns
    -0.67
     espejos
    -0.67
    フォー
    -0.66
    POSITIVE LOGITS
     odstran
    0.76
     inanimate
    0.68
    gha
    0.67
    abı
    0.67
    jalá
    0.66
     спорта
    0.66
    ᴥ
    0.66
    ⎕
    0.65
    Schüler
    0.65
    Concern
    0.64
    Activations Density 0.084%

    No Known Activations