© 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. 4304
    Prev
    Next
    INDEX
    Explanations

    whose + noun phrase

    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
    t
    1.99
    𝗻
    1.70
    n
    1.67
    𝗳
    1.52
    tive
    1.49
    ли
    1.49
    rising
    1.48
    e
    1.42
    Farmer
    1.41
    но
    1.39
    POSITIVE LOGITS
     fratt
    1.31
     cuya
    1.29
     কিনা
    1.25
    그러나
    1.23
     Adapun
    1.19
    elsk
    1.13
    ীতে
    1.12
     Verwendung
    1.12
     উদ্যোগে
    1.11
     excitations
    1.10
    Activations Density 0.007%

    No Known Activations