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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1234
    Prev
    Next
    INDEX
    Explanations

    собирать, солнце, содержание

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    cccccc
    1.55
    ীয়
    1.51
    the
    1.50
    '
    1.50
    শীল
    1.49
    we
    1.46
    ्स
    1.44
    INE
    1.44
    they
    1.41
    cccc
    1.39
    POSITIVE LOGITS
    ៊ី
    1.96
     bastante
    1.65
    大量的
    1.65
    很多的
    1.59
    nání
    1.57
     '*':
    1.57
     প্রচুর
    1.56
    ilder
    1.53
     огромное
    1.53
     ‘
    1.52
    Activations Density 0.251%

    No Known Activations