© 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. 2969
    Prev
    Next
    INDEX
    Explanations

    shorter, 5th, est, ink

    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
    い
    1.36
    бы
    1.27
     Webseite
    1.25
    بالإنجليزية
    1.21
     aeg
    1.21
    ে
    1.20
     meest
    1.19
     föret
    1.19
    cina
    1.19
     ненави
    1.18
    POSITIVE LOGITS
    payers
    1.20
    tych
    1.01
     recalling
    0.97
     friendly
    0.96
     alarmed
    0.96
    +,
    0.96
    ContentLoaded
    0.95
    ส์
    0.94
     loyal
    0.92
     chilled
    0.91
    Activations Density 0.005%

    No Known Activations