© 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. 2645
    Prev
    Next
    INDEX
    Explanations

    sequencing and translation

    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
     exacerb
    0.71
     chiral
    0.69
     exacerbate
    0.68
     conventionally
    0.66
     aerosol
    0.65
     resultante
    0.63
     convencional
    0.62
    祸
    0.61
     incorporating
    0.61
     sparsity
    0.61
    POSITIVE LOGITS
    ৬
    0.83
    dyž
    0.80
     треба
    0.78
     ৭
    0.78
    IENCE
    0.78
    ISATION
    0.76
     هایی
    0.76
    <0x95>
    0.75
    გრამ
    0.75
    IENT
    0.74
    Activations Density 0.063%

    No Known Activations