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. 22-GEMMASCOPE-2-RES-16K
    4. 1372
    Prev
    Next
    INDEX
    Explanations

    question starting phrases

    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
     ત્યારબાદ
    1.16
     🙏
    1.13
    तियाँ
    1.10
     enquiries
    1.09
    🙏🏻
    1.08
    🙏
    1.06
    🔄
    1.05
     सम्बंधित
    1.04
     onwards
    1.03
     जाँच
    1.02
    POSITIVE LOGITS
     —
    1.18
     enggak
    1.14
     nonprofit
    1.07
     longtime
    1.02
    妩
    1.01
    five
    0.99
    really
    0.97
     phony
    0.96
     ­
    0.96
     বেশির
    0.94
    Activations Density 0.072%

    No Known Activations