© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10079
    Prev
    Next
    INDEX
    Explanations

    technical or personal information

    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_16k_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
     flex
    0.91
     renting
    0.90
     uczni
    0.89
    берём
    0.89
    ार्मिक
    0.88
    <%=
    0.88
    郯
    0.87
    cstdio
    0.87
     compacted
    0.86
     ceiling
    0.85
    POSITIVE LOGITS
    a
    1.33
    ä
    1.03
     sfor
    1.01
    𝖽
    1.00
    age
    0.98
     laughs
    0.97
    ğe
    0.97
     Constants
    0.96
    া
    0.93
    eit
    0.93
    Activations Density 0.000%

    No Known Activations