© 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. 14690
    Prev
    Next
    INDEX
    Explanations

    woman would have

    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
    い
    1.50
     settles
    1.21
     unusually
    1.19
     blanket
    1.18
     deutsch
    1.17
    ών
    1.15
     defensive
    1.15
     interrogation
    1.13
     neurologist
    1.13
     fence
    1.11
    POSITIVE LOGITS
    ವಾ
    1.32
     distinta
    1.13
    drying
    1.13
    т
    1.11
     riqueza
    1.11
     pública
    1.06
    માં
    1.05
    ной
    1.05
     innymi
    1.04
    ग्विजय
    1.04
    Activations Density 0.003%

    No Known Activations