© 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. 10506
    Prev
    Next
    INDEX
    Explanations

    name queries

    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
    ым
    2.63
    ский
    2.41
    dental
    2.40
     exclaimed
    2.37
    n
    2.11
     quarts
    2.10
     никакого
    2.08
    ंनो
    2.07
    اته
    2.06
    ный
    2.06
    POSITIVE LOGITS
    चीन
    2.57
     زمانہ
    2.50
    riad
    2.36
    古屋
    2.35
    ட்சத்திர
    2.27
    iddag
    2.24
    꼴
    2.16
    subdir
    2.13
     석
    2.06
    زد
    2.04
    Activations Density 0.166%

    No Known Activations