© 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. 109012
    Prev
    Next
    INDEX
    Explanations

    under conditions or warranty

    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
    stylesheet
    -0.87
     llan
    -0.80
    digheden
    -0.79
     palab
    -0.77
     came
    -0.77
    ⤵
    -0.75
     Çe
    -0.75
     tangible
    -0.73
     became
    -0.73
     classico
    -0.73
    POSITIVE LOGITS
     artículo
    0.94
    ENTS
    0.85
    distrito
    0.82
     bình
    0.81
     الماء
    0.79
     供
    0.78
    igg
    0.77
     arbres
    0.77
    ουν
    0.76
     probablemente
    0.76
    Activations Density 0.002%

    No Known Activations