© 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. 8193
    Prev
    Next
    INDEX
    Explanations

    as

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

    as

    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
     SSA
    0.41
    抧
    0.34
     osh
    0.34
     அடைய
    0.33
    ssc
    0.33
    ProgressListener
    0.33
     Dutt
    0.33
    LOUISE
    0.32
     আচার
    0.32
    咘
    0.32
    POSITIVE LOGITS
    as
    2.36
    As
    2.25
     As
    2.22
    AS
    1.95
     AS
    1.73
     as
    1.48
    ās
    1.34
    اس
    1.32
    AsString
    1.30
    ás
    1.28
    Activations Density 0.133%

    No Known Activations