© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8669
    Prev
    Next
    INDEX
    Explanations

    property ownership and characteristics

    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_262k_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
    ة
    2.06
    к
    1.82
    ת
    1.68
    κ
    1.57
     rhetorical
    1.56
     rhetoric
    1.54
    ed
    1.45
    ް
    1.44
    돠
    1.42
    ்கு
    1.37
    POSITIVE LOGITS
    ו
    1.61
    睨
    1.47
    tty
    1.43
    👉
    1.42
    ttt
    1.39
     começ
    1.38
    তে
    1.37
    जन
    1.36
    
    1.34
    ں
    1.32
    Activations Density 0.096%

    No Known Activations