© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    get the most out

    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
     والصلاه
    0.81
     Euh
    0.79
     poised
    0.78
    淉
    0.74
     shortly
    0.73
     फाइन
    0.73
    㷫
    0.72
     favourably
    0.72
     কর্তৃক
    0.71
    悳
    0.71
    POSITIVE LOGITS
     maximum
    1.17
    maximum
    1.05
     out
    1.03
     Maximum
    0.96
     maximal
    0.91
     max
    0.88
     maximale
    0.88
    max
    0.86
     maksimal
    0.86
     максима
    0.85
    Activations Density 0.093%

    No Known Activations