© 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-262K
    4. 43185
    Prev
    Next
    INDEX
    Explanations

    rim lighting

    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
     tcpHeader
    0.52
     مي‌
    0.50
     божомолу
    0.50
     બના
    0.49
    OutputDir
    0.48
    Manisha
    0.48
     但
    0.48
    ’-
    0.46
    }.$$
    0.46
     crumbled
    0.46
    POSITIVE LOGITS
    ا
    0.45
    ային
    0.44
     of
    0.43
     nel
    0.42
    odom
    0.42
     algorithms
    0.42
    মতো
    0.42
     affirmation
    0.41
    ho
    0.41
     a
    0.41
    Activations Density 0.001%

    No Known Activations