© 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. 63040
    Prev
    Next
    INDEX
    Explanations

    former local government areas

    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
     Punt
    -0.85
    Ebook
    -0.74
    ASG
    -0.73
    punt
    -0.70
    AHUL
    -0.68
    bingo
    -0.68
    BARA
    -0.67
     chapter
    -0.67
    Punt
    -0.67
     bedo
    -0.67
    POSITIVE LOGITS
    ADX
    0.75
     negativas
    0.73
     epigenetic
    0.69
    льник
    0.68
    lanmış
    0.66
    郑州
    0.66
     низ
    0.65
     Chester
    0.65
    连接
    0.65
    fashion
    0.65
    Activations Density 0.078%

    No Known Activations