© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 14412
    Prev
    Next
    INDEX
    Explanations

    turn off, on, around, right

    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
    勬
    2.15
     darn
    2.14
     quero
    2.08
     оттен
    2.04
    ява
    2.02
     ASE
    2.02
     dang
    1.98
     EPO
    1.97
    勮
    1.96
     Avid
    1.93
    POSITIVE LOGITS
    pike
    2.78
    arounds
    2.30
    eau
    2.20
    एस
    2.00
    e
    1.98
    ्हा
    1.94
    ون
    1.91
    around
    1.84
     sufferers
    1.83
     vẻ
    1.82
    Activations Density 0.477%

    No Known Activations