© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102488
    Prev
    Next
    INDEX
    Explanations

    secondary [noun]

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

    secondary to other conditions

    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_31_width_262k_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
    是有
    0.44
    ropolis
    0.43
     yǒu
    0.41
    そして
    0.41
    networks
    0.40
    मॉ
    0.40
    ството
    0.40
    漼
    0.40
    及
    0.39
    綏
    0.39
    POSITIVE LOGITS
     Secondary
    0.63
     secondary
    0.59
    secondary
    0.58
    0.57
    Secondary
    0.55
    SECONDARY
    0.52
     सेकेंडरी
    0.51
     тільки
    0.49
     secundaria
    0.49
     names
    0.48
    Activations Density 0.002%

    No Known Activations