© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 193
    Prev
    Next
    INDEX
    Explanations

    people in roles and relative clauses

    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_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
     exploded
    0.31
    	
    0.30
    text
    0.30
     x
    0.30
    label
    0.29
     &=
    0.29
     was
    0.28
     bytes
    0.28
     ');
    0.28
     used
    0.28
    POSITIVE LOGITS
     ktorí
    0.53
     quienes
    0.49
     who
    0.47
     quien
    0.44
     którzy
    0.43
     الذين
    0.42
     whom
    0.41
    에게
    0.39
     kteří
    0.38
     जिन्होंने
    0.38
    Activations Density 1.149%

    No Known Activations