© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

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

    identifying quantities in lists

    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
     ২টি
    0.85
     ১ম
    0.78
     ৪র্থ
    0.75
    第
    0.66
     ৯ম
    0.61
     ৮ম
    0.49
    ㅄ
    0.49
     ৫ম
    0.47
     ½
    0.43
     aprox
    0.43
    POSITIVE LOGITS
     seven
    2.75
     five
    2.69
     six
    2.66
     eight
    2.66
    five
    2.55
     nine
    2.50
    six
    2.48
    seven
    2.44
    eight
    2.34
     four
    2.31
    Activations Density 0.702%

    No Known Activations