© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    common noun + conjunction/punctuation

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

    or

    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
    0.32
     (
    0.25
    ↵
    0.25
     “
    0.25
     the
    0.24
    ?
    0.24
    ,
    0.24
     cabinets
    0.22
      
    0.21
    _
    0.21
    POSITIVE LOGITS
     Caedwalla
    0.28
     nisid
    0.27
     esemplare
    0.27
     imassa
    0.27
     vasena
    0.27
    autoarima
    0.27
     esemplari
    0.26
     yattha
    0.26
     libertà
    0.26
    వెట్‌
    0.26
    Activations Density 0.458%

    No Known Activations