© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    positive terms followed by common nouns

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

    forms of, more than, odd numbers

    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
     "
    0.38
     "..
    0.38
     "...
    0.37
    ஃ
    0.36
    ifiably
    0.35
     Amerikaanse
    0.34
    inkl
    0.34
    0.34
     tertentu
    0.33
    ភ
    0.33
    POSITIVE LOGITS
    swering
    1.06
    此之外
    1.05
    ostante
    1.04
    kaç
    0.98
    cknowled
    0.97
    mselves
    0.97
    neath
    0.88
    evším
    0.88
    atrical
    0.88
    oretically
    0.87
    Activations Density 1.036%

    No Known Activations