© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1714
    Prev
    Next
    INDEX
    Explanations

    title and subject 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_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
    Nicole
    -0.82
    CÓMO
    -0.79
     revés
    -0.78
    gaande
    -0.78
    oweit
    -0.78
    久し
    -0.77
    いきなり
    -0.77
    ﺠ
    -0.76
    demie
    -0.76
    gyű
    -0.74
    POSITIVE LOGITS
     financiera
    0.80
    rouvez
    0.79
     classifying
    0.78
    calientes
    0.77
    ATTER
    0.77
    andidat
    0.76
     Investigators
    0.76
     compound
    0.74
    ❘
    0.73
    segu
    0.72
    Activations Density 0.002%

    No Known Activations