© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    stone, concrete, cement, rocks

    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_22_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
    🎪
    0.89
     Fluorescence
    0.84
    🎡
    0.82
    foldername
    0.81
    翎
    0.80
     treetops
    0.80
     fadeIn
    0.79
    𝜆
    0.79
     Sacchar
    0.79
    煙
    0.78
    POSITIVE LOGITS
     stone
    2.25
     stones
    2.21
     Stone
    1.91
    石
    1.87
     Stones
    1.78
     STONE
    1.75
     rocks
    1.74
    Stone
    1.73
    stone
    1.71
     granite
    1.70
    Activations Density 0.250%

    No Known Activations