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. 7300
    Prev
    Next
    INDEX
    Explanations

    criteria used

    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
     मचा
    2.35
     conspicuous
    2.24
    員
    2.18
     forth
    2.10
    aż
    2.09
    ्या
    2.02
    ்கு
    2.01
    is
    1.99
    ਾਨ
    1.98
    uten
    1.97
    POSITIVE LOGITS
    re
    2.47
    एं
    2.42
    최
    2.16
    การ
    1.99
    st
    1.98
    Пол
    1.97
    Après
    1.96
    যুক্ত
    1.93
    ٢
    1.90
     anteced
    1.87
    Activations Density 0.067%

    No Known Activations