© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    Astrophysics, Kansas City, grant for

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

    public guidelines for safety

    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
    等等
    0.38
    」、「
    0.37
    (!)
    0.36
    𝗙
    0.36
    "+"
    0.36
     "+"
    0.36
     "
    0.35
    ','
    0.34
     "****
    0.34
    𝙨
    0.34
    POSITIVE LOGITS
     ción
    0.57
     tions
    0.52
     tion
    0.44
     tional
    0.42
     sion
    0.41
     ular
    0.41
     tive
    0.41
     ments
    0.40
     cated
    0.38
    pués
    0.38
    Activations Density 0.667%

    No Known Activations