© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19320
    Prev
    Next
    INDEX
    Explanations

    capture, chase, or apprehend

    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
     omitted
    0.50
     omissions
    0.44
    嫂
    0.43
    讖
    0.42
     ideological
    0.41
    Parsed
    0.41
    Chunks
    0.40
     misinterpreted
    0.40
    解放
    0.38
     pInBuffer
    0.38
    POSITIVE LOGITS
     capture
    0.93
    capture
    0.89
    捕
    0.87
     Capture
    0.85
    Capture
    0.84
    捕捉
    0.78
    追
    0.76
     chase
    0.73
     captura
    0.72
     catching
    0.71
    Activations Density 0.047%

    No Known Activations