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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7513
    Prev
    Next
    INDEX
    Explanations

    reading and code execution

    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
    semester
    1.35
    uid
    1.33
    ende
    1.22
    lang
    1.17
    𝐫
    1.17
    孔
    1.16
     okaz
    1.16
    اول
    1.14
    वार
    1.12
    BEC
    1.10
    POSITIVE LOGITS
    ی
    2.51
    ি
    1.85
     readFile
    1.78
    י
    1.68
     Incluso
    1.61
     ethylene
    1.59
    asang
    1.51
    ੀ
    1.49
    یی
    1.49
    ி
    1.48
    Activations Density 0.000%

    No Known Activations