© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8330
    Prev
    Next
    INDEX
    Explanations

    simple [descriptor]

    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
    ي
    2.78
    al
    2.27
    ை
    2.25
    ০
    2.17
    as
    2.17
    氇
    2.11
    ل
    2.08
    و
    2.07
     sampled
    2.03
    ك
    2.02
    POSITIVE LOGITS
    ैम
    2.11
    ت
    1.98
    houette
    1.94
    minded
    1.93
    ധാന
    1.91
    
    1.84
    verständlich
    1.83
    tive
    1.83
    ্ভব
    1.82
    üedad
    1.81
    Activations Density 0.431%

    No Known Activations