© 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. 14747
    Prev
    Next
    INDEX
    Explanations

    health, disease, fiction, and specific 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
    ar
    1.16
     Increase
    1.13
     höchsten
    1.12
    ن
    1.10
     Entire
    1.06
     Large
    1.04
     యొక్క
    1.02
    ন
    1.02
    ोलिक
    1.02
    ال
    1.01
    POSITIVE LOGITS
    efficacy
    1.32
     thwarted
    1.31
    Zimbabwe
    1.24
    ować
    1.24
    mary
    1.21
     pabbaj
    1.17
    larını
    1.17
    <unused1793>
    1.16
     discredited
    1.16
    concatenate
    1.16
    Activations Density 0.019%

    No Known Activations