© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111035
    Prev
    Next
    INDEX
    Explanations

    additional gifts

    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
    vyš
    -0.87
    constructor
    -0.85
     yerde
    -0.83
     prophets
    -0.80
     Thoreau
    -0.79
     contributors
    -0.79
    wußt
    -0.79
    ستخدم
    -0.78
     Paulo
    -0.78
     GMT
    -0.77
    POSITIVE LOGITS
     ObjectParameter
    0.81
    fler
    0.77
    <em>
    0.77
    ⊨
    0.76
     including
    0.76
    towy
    0.76
    enetrable
    0.75
     include
    0.74
     razón
    0.73
     Архивировано
    0.73
    Activations Density 0.009%

    No Known Activations