© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    here's or here are introducing content

    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
    ύ
    1.77
    अगर
    1.77
     Такой
    1.73
    Ꮬ
    1.71
     FIXME
    1.70
    ünü
    1.67
     выполнять
    1.63
    货币
    1.63
     다음과
    1.61
    если
    1.61
    POSITIVE LOGITS
    an
    2.06
    at
    2.00
    на
    1.86
    inafter
    1.86
    ا
    1.79
    저
    1.75
     നിന്ന്
    1.74
    𝑣
    1.70
     ওখানে
    1.70
    jší
    1.66
    Activations Density 0.377%

    No Known Activations