© 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. 63402
    Prev
    Next
    INDEX
    Explanations

    names containing 'un'

    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
     Maybe
    -0.90
     like
    -0.85
     Lainnya
    -0.84
    erecht
    -0.83
    größe
    -0.81
    goods
    -0.81
    ضي
    -0.80
    dubbo
    -0.79
    oubted
    -0.78
    dhi
    -0.77
    POSITIVE LOGITS
    nery
    1.02
    ned
    0.99
    nin
    0.97
    niest
    0.97
    nit
    0.96
    nen
    0.96
    nnnn
    0.94
    nal
    0.93
    ners
    0.91
    ni
    0.90
    Activations Density 0.031%

    No Known Activations