© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 160
    Prev
    Next
    INDEX
    Explanations

    related or suggested content

    np_acts-logits-general · gemini-2.5-flash-lite

    recommendations and related items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h1>
    0.61
    <h4>
    0.57
    <h3>
    0.51
    <h6>
    0.49
    <h5>
    0.41
    <table>
    0.40
    <h2>
    0.40
    interaction
    0.36
     laden
    0.35
        
    0.35
    POSITIVE LOGITS
     RELATED
    0.89
     Related
    0.86
    Related
    0.85
     Similar
    0.82
    Similar
    0.82
     related
    0.80
     similar
    0.79
     관련
    0.78
    RELATED
    0.77
    関連
    0.76
    Activations Density 0.001%

    No Known Activations