© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    words starting with cre

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

    cre cream creature creative

    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
    жон
    0.37
    ্ঠ
    0.36
     clearContext
    0.36
    打造
    0.36
    getTargetContext
    0.36
     whanne
    0.35
     రాజ
    0.34
    ժ
    0.34
    hydrocèle
    0.34
    objc
    0.34
    POSITIVE LOGITS
     кре
    3.97
    cre
    3.66
     cre
    3.66
    Cre
    3.64
     Cre
    3.53
     kre
    3.52
    CRE
    3.50
     CRE
    3.48
     Кре
    3.48
     Kre
    3.41
    Activations Density 0.251%

    No Known Activations