© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204874
    Prev
    Next
    INDEX
    Explanations

    sources, confidence, confirm, find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    virtual
    0.39
    Bollywood
    0.39
     bl
    0.39
    虚拟
    0.39
     Bollywood
    0.38
    ![](
    0.37
     Cang
    0.37
    j
    0.37
    submission
    0.36
     Rip
    0.36
    POSITIVE LOGITS
     ഇന്ന
    0.43
     ૧
    0.43
    ༸
    0.42
    దల
    0.41
     clairement
    0.41
    
    0.41
     सूत्रकृमि
    0.40
     MgO
    0.40
    䤚
    0.40
     अग्रणी
    0.39
    Activations Density 0.006%

    No Known Activations