© 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. 357
    Prev
    Next
    INDEX
    Explanations

    numbers and conditions

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

    Human Feedback

    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
    Մ
    0.61
    0.59
    ５
    0.58
    ୫
    0.58
    memset
    0.58
     ۵
    0.56
    ۵
    0.55
    ৫
    0.55
    ༥
    0.55
    明確
    0.54
    POSITIVE LOGITS
    aları
    0.46
    8
    0.46
    <ul>
    0.44
     prostor
    0.43
    など
    0.41
     그리고
    0.41
    ১৮
    0.41
    Princeton
    0.40
    ="#"
    0.40
     தொடர்ந்து
    0.40
    Activations Density 0.408%

    No Known Activations