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. 17-GEMMASCOPE-2-RES-65K
    4. 47243
    Prev
    Next
    INDEX
    Explanations

    burgeoning populations, hyperedge, lack resources, tax obligations

    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_65k_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
     reconstituted
    1.08
    ์
    1.07
    he
    1.01
     sens
    0.98
     مدی
    0.98
     پکڑ
    0.94
    ச்
    0.93
     tangan
    0.91
     dob
    0.89
    ار
    0.89
    POSITIVE LOGITS
    ^*_{
    1.27
    ᓲ
    1.24
    वा
    1.22
    ^*(
    1.21
     _{\
    1.19
    ْم
    1.19
     agrícolas
    1.16
    }^{+}(
    1.15
     JButton
    1.15
     война
    1.15
    Activations Density 0.005%

    No Known Activations