© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57151
    Prev
    Next
    INDEX
    Explanations

    chef, comedian, director names

    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
     dumplings
    -0.85
     运
    -0.81
     GHS
    -0.76
    ウト
    -0.74
     sagit
    -0.74
     implan
    -0.72
     Kark
    -0.72
     ammon
    -0.71
    捜査
    -0.69
     intuiti
    -0.69
    POSITIVE LOGITS
    琮
    0.90
     соль
    0.85
     Aziz
    0.80
    magyar
    0.77
    中小
    0.74
     autó
    0.73
     АК
    0.73
    Witness
    0.73
     acides
    0.72
    ctivo
    0.71
    Activations Density 0.008%

    No Known Activations