© 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. 10-GEMMASCOPE-RES-131K
    7. 39213
    Prev
    Next
    INDEX
    Explanations

    iHeartMedia

    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_10/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
    ıştı
    -1.75
    
    -1.70
    蚡
    -1.69
    ٦
    -1.67
    聼
    -1.66
     새로운
    -1.66
    GOV
    -1.66
    姽
    -1.66
    🫅
    -1.65
     eixo
    -1.59
    POSITIVE LOGITS
    When
    2.16
    The
    2.11
    when
    2.06
    because
    1.99
    e
    1.94
    Because
    1.84
    after
    1.80
    //
    1.79
    on
    1.76
    with
    1.74
    Activations Density 0.107%

    No Known Activations