Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 600
    Prev
    Next
    INDEX
    Explanations

    numerical years

    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_16_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
     که
    0.38
    _
    0.38
    ຂອງ
    0.36
     που
    0.36
    of
    0.35
    یم
    0.35
    ಗಳನ್ನು
    0.34
    که
    0.33
    が
    0.33
     від
    0.33
    POSITIVE LOGITS
    ين
    0.61
    на
    0.51
    h
    0.49
    g
    0.43
    ne
    0.42
    c
    0.41
    ال
    0.40
    z
    0.40
    r
    0.40
    k
    0.39
    Activations Density 13.603%

    No Known Activations