© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    subject and topic

    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
    pä
    2.68
    ping
    2.56
    ment
    2.49
    siniz
    2.46
    på
    2.39
     уж
    2.31
    %%%%%%%%
    2.26
    водить
    2.22
    и
    2.21
    ưởng
    2.20
    POSITIVE LOGITS
    বস্ত
    2.46
     विकार
    2.33
     tinc
    2.25
    শ্রে
    2.22
     disinfect
    2.21
     Etern
    2.19
     regeneration
    2.18
     deprived
    2.17
     बातों
    2.15
     monologue
    2.14
    Activations Density 0.188%

    No Known Activations