© 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. 17260
    Prev
    Next
    INDEX
    Explanations

    rabat, jira, fresh file paths

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

    scikit, gensim, spring

    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
    Com
    0.46
    3
    0.45
    Impl
    0.41
     충
    0.40
    _
    0.39
    Name
    0.38
    2
    0.38
    +
    0.38
    Lock
    0.37
    Logic
    0.37
    POSITIVE LOGITS
    າມາດ
    0.47
     ilmu
    0.47
     laboratoire
    0.46
    ঞ্জের
    0.44
    ঢাকা
    0.42
    स्ट्रेल
    0.42
    watercolor
    0.42
     základ
    0.41
    ন্দরী
    0.41
    lovepoetry
    0.41
    Activations Density 0.014%

    No Known Activations