© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73731
    Prev
    Next
    INDEX
    Explanations

    code file headers

    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_22/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
    }.
    -0.99
     things
    -0.96
    </h2>
    -0.87
    /}.
    -0.83
    <h2>
    -0.82
    》。
    -0.80
    "].
    -0.80
    af
    -0.78
    ");
    -0.78
     ursprüng
    -0.77
    POSITIVE LOGITS
     fleste
    0.89
    утбо
    0.88
     vlož
    0.84
    」(
    0.84
    岭
    0.83
    cosplay
    0.83
    missao
    0.82
     nivå
    0.82
     vienas
    0.82
    而是
    0.81
    Activations Density 0.081%

    No Known Activations