© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2094
    Prev
    Next
    INDEX
    Explanations

    be followed by verb

    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_9_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
    an
    2.15
    서
    1.90
    ك
    1.78
    ma
    1.74
     supposed
    1.71
    к
    1.58
    nt
    1.56
    duplicates
    1.49
    e
    1.48
    k
    1.47
    POSITIVE LOGITS
    salad
    1.73
    িণী
    1.72
     сколько
    1.60
    ים
    1.55
     joked
    1.49
    ርግ
    1.47
    टर
    1.44
     dicho
    1.43
    いる
    1.42
    ুল
    1.42
    Activations Density 0.244%

    No Known Activations