© 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. 17-GEMMASCOPE-2-RES-16K
    7. 11836
    Prev
    Next
    INDEX
    Explanations

    USA, Australia, spider, arr

    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
    اً
    1.33
    .*;
    1.11
    مة
    1.09
    ۔
    1.09
     сма
    1.08
    めます
    1.06
    Σ
    1.04
    |\
    1.04
    મારી
    1.00
    ۰۰
    0.97
    POSITIVE LOGITS
     evoc
    1.24
     california
    1.17
     unwilling
    1.15
     anon
    1.13
     împ
    1.11
     rebut
    1.11
     voluto
    1.10
     anise
    1.09
     quotid
    1.09
    માં
    1.08
    Activations Density 0.002%

    No Known Activations