© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 200
    Prev
    Next
    INDEX
    Explanations

    negations using do not / does not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kleiner
    0.36
    ‑
    0.36
     ​​​​
    0.34
     ose
    0.33
     nie
    0.33
     weiterer
    0.32
     \
    0.32
    ​
    0.32
     liegt
    0.32
     ei
    0.31
    POSITIVE LOGITS
    effectuer
    0.50
     गोइंग
    0.49
     कॉल्ड
    0.46
     تصميم
    0.45
    Pyrid
    0.45
    ፑ
    0.44
    Hydrochloride
    0.43
    Điều
    0.42
    PropertyList
    0.42
     أفضل
    0.42
    Activations Density 0.430%

    No Known Activations