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. 17-GEMMASCOPE-2-RES-65K
    4. 1570
    Prev
    Next
    INDEX
    Explanations

    location adjectives

    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_65k_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
    璀
    0.35
     tems
    0.34
     recal
    0.34
     longiore
    0.33
     proverbial
    0.33
     звуча
    0.33
     represent
    0.32
     justifica
    0.32
     diversi
    0.32
    ляє
    0.32
    POSITIVE LOGITS
    ց
    0.49
    ירות
    0.44
    nik
    0.41
    ny
    0.41
    isto
    0.41
    קו
    0.41
    מו
    0.41
    То
    0.40
     nowadays
    0.40
    Raymond
    0.40
    Activations Density 0.000%

    No Known Activations