© 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. 138324
    Prev
    Next
    INDEX
    Explanations

    even social

    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
    enje
    0.45
    ा
    0.43
    Way
    0.42
    )
    0.42
    期间
    0.41
    ir
    0.40
    ib
    0.40
    ílio
    0.40
    ik
    0.39
     GIF
    0.39
    POSITIVE LOGITS
     communicating
    0.48
     الطيب
    0.45
     bonnes
    0.44
     Hades
    0.44
    会話
    0.43
     बैक्टीरिया
    0.42
     batería
    0.42
    gehen
    0.41
    姉
    0.41
    <0x95>
    0.41
    Activations Density 0.001%

    No Known Activations