© 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. 117128
    Prev
    Next
    INDEX
    Explanations

    Ukrainian and other Slavic languages

    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
    ̒
    -0.77
    lē
    -0.75
    getResult
    -0.71
    textview
    -0.69
    Rafael
    -0.69
    Ered
    -0.68
    stackoverflow
    -0.66
    uminescence
    -0.65
     erinner
    -0.65
     rũ
    -0.65
    POSITIVE LOGITS
    ione
    0.83
     existem
    0.83
     gab
    0.82
    ])/
    0.76
    ción
    0.75
    eramente
    0.74
    scrollY
    0.74
    ˎ
    0.74
    ]^
    0.72
    tima
    0.71
    Activations Density 0.001%

    No Known Activations