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. 22-GEMMASCOPE-2-RES-65K
    4. 280
    Prev
    Next
    INDEX
    Explanations

    hyp, hacking, HTML

    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_22_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
    ሖ
    1.28
     hukum
    1.21
     хорошее
    1.20
     hyperfine
    1.19
     высоту
    1.15
     совсем
    1.15
     جمله
    1.14
     SSP
    1.12
    hard
    1.12
     উপযুক্ত
    1.11
    POSITIVE LOGITS
     sapiens
    1.99
     gxh
    1.72
     pylori
    1.60
    izontal
    1.45
    萏
    1.42
    élène
    1.41
    چل
    1.37
    aplic
    1.37
    ຼ
    1.32
    ঠাৎ
    1.29
    Activations Density 1.105%

    No Known Activations