© 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. 8268
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs of knowing or admitting

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

    I understand, but can't

    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
     думаю
    0.45
     ipv
    0.44
    我觉得
    0.44
     오히려
    0.43
     pts
    0.43
     dlr
    0.42
    囦
    0.42
    我覺得
    0.41
     Definitely
    0.41
    ຢ
    0.40
    POSITIVE LOGITS
     mentioned
    0.58
     alluded
    0.57
     digress
    0.56
     wspom
    0.55
     bukanlah
    0.53
     confess
    0.52
     erwäh
    0.52
     knew
    0.51
     mencionó
    0.51
     admitted
    0.50
    Activations Density 0.169%

    No Known Activations