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. 8170
    Prev
    Next
    INDEX
    Explanations

    Z followed by letters or numbers

    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
    шого
    3.45
    ⺆
    3.06
    न
    2.92
    stit
    2.90
     जमकर
    2.89
    iendo
    2.79
    шою
    2.74
    lijk
    2.74
    шої
    2.74
    هام
    2.74
    POSITIVE LOGITS
    IRCONIUM
    4.17
    ়
    3.05
    ્ઞ
    3.01
    ariah
    2.81
     iya
    2.76
    agoza
    2.76
    з
    2.71
     entails
    2.66
    ャ
    2.66
    ্যেষ্ঠ
    2.65
    Activations Density 0.170%

    No Known Activations