© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17428
    Prev
    Next
    INDEX
    Explanations

    quoted text

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

    open ended, challenging, or strange

    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
    {
    0.46
    OR
    0.43
     autori
    0.43
     garde
    0.43
    newcommand
    0.42
    noindent
    0.42
     ca
    0.41
     src
    0.41
    html
    0.40
    ُم
    0.39
    POSITIVE LOGITS
    さんが
    0.43
     सीजन
    0.40
    ᖕ
    0.40
    さんも
    0.40
     достой
    0.39
    গ্রামে
    0.39
     पर्सनल
    0.38
     अखिल
    0.38
     "#
    0.38
     unarmed
    0.38
    Activations Density 0.000%

    No Known Activations