© 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. 29-GEMMASCOPE-2-RES-16K
    7. 401
    Prev
    Next
    INDEX
    Explanations

    possessive names or general descriptions

    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_29_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
     क्लाइ
    0.65
    Regional
    0.64
     hayvan
    0.64
    Police
    0.61
     সংখ্যাগরিষ্ঠ
    0.60
     Regional
    0.60
    凋
    0.60
    ICH
    0.59
     Tully
    0.59
    ionu
    0.59
    POSITIVE LOGITS
    ادة
    0.59
     б
    0.58
    成年
    0.58
    联赛
    0.56
    废
    0.55
     விரு
    0.55
     ノー
    0.53
    ப்பிர
    0.52
    ayt
    0.52
    betriebnahme
    0.52
    Activations Density 0.471%

    No Known Activations