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. 7484
    Prev
    Next
    INDEX
    Explanations

    more Evocative

    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
     defam
    2.64
    ना
    2.58
    ৯
    2.55
    ש
    2.48
    ные
    2.44
     скорее
    2.41
    𝐼
    2.40
    ंत्रिक
    2.40
    ब्दिक
    2.38
     день
    2.38
    POSITIVE LOGITS
     allá
    3.36
     importantly
    3.30
     sinned
    2.93
    দ
    2.79
    ي
    2.78
    OVER
    2.74
    kannya
    2.68
    camb
    2.55
    y
    2.53
     lanjut
    2.52
    Activations Density 0.392%

    No Known Activations