© 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. 10629
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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
    ound
    0.83
     게
    0.82
     seamlessly
    0.77
    FRI
    0.75
    ophytic
    0.75
     upravo
    0.72
    全く
    0.72
     hemen
    0.70
    iyo
    0.70
    まったく
    0.70
    POSITIVE LOGITS
    蹟
    0.88
     evoke
    0.87
     ignore
    0.82
     ignored
    0.82
     scars
    0.81
     Storia
    0.81
    राग
    0.80
     where
    0.76
     dares
    0.75
     andRow
    0.74
    Activations Density 0.169%

    No Known Activations