© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    linking descriptive words

    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
     immunological
    0.52
     hypothetical
    0.50
     prolific
    0.49
     semi
    0.49
    事情
    0.49
     respiratory
    0.46
    s
    0.46
     proliferation
    0.45
     mitigation
    0.45
     credential
    0.45
    POSITIVE LOGITS
     மற்றும்
    0.65
     ਅਤੇ
    0.65
     或
    0.64
     અને
    0.62
     είναι
    0.61
     અથવા
    0.61
    ín
    0.60
     和
    0.60
     δεν
    0.59
     geeft
    0.59
    Activations Density 0.000%

    No Known Activations