Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7679
    Prev
    Next
    INDEX
    Explanations

    and invest

    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_9_width_262k_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
    and
    1.28
     gamme
    1.23
    әне
    1.14
    д
    1.12
     advancing
    1.12
     uridine
    1.12
    న్నారు
    1.11
     Vast
    1.08
    ﮈ
    1.08
     Adv
    1.07
    POSITIVE LOGITS
    𝐞
    1.42
    𝐢
    1.33
    ní
    1.33
    اً
    1.27
    𝐳
    1.27
    nahme
    1.26
     flicker
    1.23
     flavoured
    1.21
     불구하고
    1.20
    𝘇
    1.17
    Activations Density 0.000%

    No Known Activations