© 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. 14664
    Prev
    Next
    INDEX
    Explanations

    generate [something]

    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
    ﻊ
    2.56
    grat
    2.46
     genç
    2.43
    cription
    2.40
    ouvrage
    2.35
     forego
    2.35
    ᾖ
    2.34
    ku
    2.29
    ﺢ
    2.28
    ⿱
    2.27
    POSITIVE LOGITS
    ्यारह
    3.84
    ന്ഥ
    3.11
    maßen
    2.82
    ድግዳ
    2.76
     sức
    2.74
    ীষ্ম
    2.69
     perkara
    2.69
    মাধ্যম
    2.68
    юн
    2.64
     prospecting
    2.59
    Activations Density 1.048%

    No Known Activations