© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1631
    Prev
    Next
    INDEX
    Explanations

    why is it important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    <unused2134>
    0.89
     sicuramente
    0.73
     которы
    0.73
    <unused2161>
    0.72
    લાઇ
    0.72
    即可
    0.72
     já
    0.71
     Já
    0.71
    STD
    0.69
    <unused2176>
    0.69
    POSITIVE LOGITS
     so
    1.38
    這麼
    1.17
    这么
    1.12
     So
    1.10
     such
    1.10
     এত
    1.10
     così
    1.06
    如此
    1.04
    So
    1.00
     столь
    0.97
    Activations Density 0.549%

    No Known Activations