© 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. 40-GEMMASCOPE-2-RES-262K
    4. 21187
    Prev
    Next
    INDEX
    Explanations

    network connections

    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_40_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
     FRANCISCO
    0.38
    ORES
    0.37
     সম্পাদিত
    0.36
    OCC
    0.35
    BACH
    0.35
    برى
    0.35
    𠃍
    0.35
    }=-\
    0.35
    ໃຊ
    0.35
    ፩
    0.34
    POSITIVE LOGITS
     देती
    0.47
     gathers
    0.46
    web
    0.44
    Leadership
    0.43
     Leadership
    0.43
    Life
    0.42
     तहे
    0.41
     حياة
    0.41
     include
    0.40
     Life
    0.40
    Activations Density 0.001%

    No Known Activations