© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43080
    Prev
    Next
    INDEX
    Explanations

    positional placement and control

    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
    Li
    0.46
    李
    0.45
    \
    0.45
     Li
    0.43
    这
    0.43
    mbH
    0.42
    ấc
    0.42
     swipe
    0.41
    噗
    0.40
     બીજી
    0.40
    POSITIVE LOGITS
    xcuserdata
    0.47
    assembly
    0.44
    ող
    0.43
    conditions
    0.43
     تقريبا
    0.42
    vectors
    0.42
     தொடங்கி
    0.42
     Ohio
    0.42
    history
    0.42
    цтва
    0.41
    Activations Density 0.000%

    No Known Activations