© 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. 34-GEMMASCOPE-RES-131K
    4. 109295
    Prev
    Next
    INDEX
    Explanations

    class, public, test descriptions

    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
     tandis
    -0.83
    問合せ
    -0.78
    ticons
    -0.73
     RIGHTS
    -0.70
    }());
    -0.70
     piensan
    -0.68
    ūn
    -0.68
     challenging
    -0.67
    ím
    -0.67
     está
    -0.67
    POSITIVE LOGITS
     should
    1.30
    Given
    1.08
     given
    0.96
    given
    0.92
     Given
    0.87
     Specs
    0.87
     membangun
    0.86
    ]-'
    0.85
    because
    0.85
    Should
    0.85
    Activations Density 0.030%

    No Known Activations