© 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. 4873
    Prev
    Next
    INDEX
    Explanations

    A followed by grade or phrase

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

    letter A

    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
     internalType
    0.40
    UnifiedTopology
    0.38
     Nadu
    0.35
    usescu
    0.34
    綪
    0.33
    ドウ
    0.33
    कर्ष
    0.33
    ക്ട
    0.32
    垐
    0.32
    apte
    0.31
    POSITIVE LOGITS
     A
    3.78
    A
    3.09
    Ａ
    2.98
     А
    2.53
    𝐴
    2.38
     Α
    2.16
    А
    1.97
    𝑨
    1.91
    Ⓐ
    1.80
    Α
    1.70
    Activations Density 0.577%

    No Known Activations