© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2617
    Prev
    Next
    INDEX
    Explanations

    com, per, amb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ů
    1.10
    ខ្ញ
    1.03
    łąd
    1.01
    Н
    0.96
     cioè
    0.95
     hilfre
    0.94
    НЕ
    0.94
    Я
    0.94
    ΠΟ
    0.94
     Ще
    0.93
    POSITIVE LOGITS
    various
    1.07
    the
    1.00
    neath
    0.99
    previously
    0.98
     the
    0.98
    greater
    0.95
     greater
    0.95
     various
    0.92
     every
    0.91
     wenn
    0.90
    Activations Density 0.010%

    No Known Activations