© 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. 2045
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation or symbols

    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
    紝
    0.43
    inairement
    0.36
     دیا۔
    0.35
     preocupaciones
    0.35
     itulah
    0.35
    <unused1732>
    0.35
    <unused413>
    0.34
    ⺠
    0.34
     됐다
    0.33
     fickle
    0.33
    POSITIVE LOGITS
    ):
    2.00
    ():
    1.90
     ():
    1.79
     ):
    1.73
    *:
    1.70
    :");
    1.70
    ]:
    1.69
    :</
    1.69
    }):
    1.68
    :")
    1.66
    Activations Density 0.472%

    No Known Activations