© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    s
    0.70
    {
    0.70
    em
    0.65
    这也是
    0.65
    en
    0.63
     اینکه
    0.62
    ים
    0.62
    ceived
    0.59
     uzys
    0.58
    得知
    0.58
    POSITIVE LOGITS
     Juve
    0.68
    𝑟
    0.66
     rained
    0.65
    烏
    0.63
     kerja
    0.61
    <unused2218>
    0.60
    <unused2223>
    0.59
    trt
    0.59
     Barça
    0.59
    唬
    0.59
    Activations Density 0.314%

    No Known Activations