© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2317
    Prev
    Next
    INDEX
    Explanations

    deep, depth, dig deeper

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

    deep concepts and contexts

    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
    प्ताहिक
    0.38
    ഗണ
    0.36
    犃
    0.36
    聒
    0.34
    имость
    0.34
    тын
    0.34
    _{+}-
    0.33
    انیہ
    0.33
    zyma
    0.33
    明日
    0.32
    POSITIVE LOGITS
     deep
    4.69
    deep
    4.47
    深
    4.44
     깊
    4.38
     Deep
    4.28
     глубо
    4.25
    Deep
    4.22
    深度
    4.22
     deeper
    4.09
     profond
    4.00
    Activations Density 0.552%

    No Known Activations