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. 7217
    Prev
    Next
    INDEX
    Explanations

    AI model releases and improvements

    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
    しましょう
    1.25
     benutzen
    1.14
    做的
    1.13
    することができます
    1.10
    が好き
    1.09
    就可以了
    1.08
    !!!!
    1.06
    だと思います
    1.06
    するとき
    1.06
     можете
    1.05
    POSITIVE LOGITS
     지난해
    1.23
    此前
    1.13
    据悉
    1.10
     కీలక
    1.08
     successively
    1.07
    有望
    1.07
     amid
    1.05
     తీవ్ర
    1.04
    可谓
    1.04
     zudem
    1.04
    Activations Density 0.022%

    No Known Activations