© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1098
    Prev
    Next
    INDEX
    Explanations

    ON CONFLICT, remote control

    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_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
    しい
    0.92
    ار
    0.92
     основных
    0.91
    ائِ
    0.88
    ma
    0.86
    पत
    0.85
    pdf
    0.84
    ው
    0.83
    desPort
    0.82
     económica
    0.82
    POSITIVE LOGITS
     그렇지
    1.16
     iguales
    1.13
     Här
    1.04
    ফটেন্যান্ট
    1.03
     grieving
    1.02
     TEM
    0.98
     відста
    0.97
     toliko
    0.97
     anglers
    0.96
     alarma
    0.96
    Activations Density 0.102%

    No Known Activations