© 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. 4920
    Prev
    Next
    INDEX
    Explanations

    instructional verbs

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

    rewrite the following

    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
    Spacer
    0.40
    咩
    0.40
    ………………………………
    0.39
    ――――
    0.37
    ――
    0.36
    HERE
    0.35
    ForThe
    0.35
    的那
    0.35
    तरह
    0.34
    何
    0.34
    POSITIVE LOGITS
     निम्नलिखित
    0.71
     each
    0.64
    下列
    0.64
     ∫
    0.63
     folgenden
    0.62
     siguientes
    0.59
     নিম্নলিখিত
    0.59
     følgende
    0.58
     folgender
    0.58
    以下の
    0.57
    Activations Density 0.025%

    No Known Activations