© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    programming and financial terms

    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
     natura
    0.84
     protr
    0.79
    ϭ
    0.79
     Nova
    0.77
     Linda
    0.77
     keto
    0.76
     Keto
    0.75
    كبر
    0.73
    κρα
    0.73
     Egipto
    0.73
    POSITIVE LOGITS
    }'
    0.78
    Integer
    0.66
    serializers
    0.65
    String
    0.64
    boolean
    0.64
    /*
    0.64
    ographiques
    0.63
     විසින්
    0.62
    judul
    0.61
    }"
    0.61
    Activations Density 0.001%

    No Known Activations