© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14480
    Prev
    Next
    INDEX
    Explanations

    black bean tacos

    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
    veyor
    0.98
    grimas
    0.90
    miyor
    0.84
    FhirExtension
    0.83
    ỡi
    0.82
     fortalecer
    0.81
     Drying
    0.81
    녘
    0.81
    BusinessType
    0.81
    fitri
    0.80
    POSITIVE LOGITS
     an
    0.87
     a
    0.75
     consist
    0.72
     statements
    0.70
     any
    0.70
     vest
    0.70
     ar
    0.69
     thousands
    0.69
     your
    0.68
     hundreds
    0.68
    Activations Density 0.007%

    No Known Activations