© 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. 7854
    Prev
    Next
    INDEX
    Explanations

    Asian elephant

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

    elevation or increase

    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
     Lia
    0.42
    ardia
    0.41
     lia
    0.40
     Antonio
    0.38
    㖦
    0.36
    Antonio
    0.36
    roxine
    0.36
    姣
    0.36
     Krause
    0.35
    Formatter
    0.35
    POSITIVE LOGITS
    Elev
    3.92
     Elev
    3.91
     ELE
    3.86
     ele
    3.84
     elev
    3.84
    elev
    3.83
     Ele
    3.78
     elevation
    3.72
     elevate
    3.70
    Ele
    3.69
    Activations Density 0.157%

    No Known Activations