© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166429
    Prev
    Next
    INDEX
    Explanations

    technical terms and uncertainty

    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
     Mechanisms
    0.41
     issuance
    0.41
    常用的
    0.39
     基于
    0.39
    满足
    0.39
    Vai
    0.39
    poses
    0.38
    ἅ
    0.38
    шать
    0.37
    用心
    0.37
    POSITIVE LOGITS
    onski
    0.41
     ongles
    0.40
    onz
    0.38
    contentInset
    0.38
     pund
    0.38
     নিশ্চয়
    0.38
     ஓடுப
    0.38
     তেল
    0.38
    ొప్ప
    0.38
     onun
    0.38
    Activations Density 0.002%

    No Known Activations