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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1829
    Prev
    Next
    INDEX
    Explanations

    public health and institutions

    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_29_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
    berger
    0.78
    빵
    0.74
    eg
    0.72
    வார
    0.68
    Suggest
    0.68
     తల్లి
    0.66
    شمند
    0.65
    בד
    0.64
    ρός
    0.63
    ̖
    0.63
    POSITIVE LOGITS
     sector
    1.33
    sector
    1.31
     Enemy
    1.26
     Sector
    1.22
    ally
    1.20
     servants
    1.20
     outcry
    1.18
     opinion
    1.17
     relations
    1.15
     domain
    1.13
    Activations Density 0.133%

    No Known Activations