© 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. 134572
    Prev
    Next
    INDEX
    Explanations

    at first glance

    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
    ("**
    0.42
    thememanager
    0.40
     neural
    0.39
     denke
    0.39
    朹
    0.38
     гульнявыя
    0.38
     해주
    0.38
    フレーム
    0.38
    我觉得
    0.37
     hätten
    0.37
    POSITIVE LOGITS
     superficially
    1.26
     glance
    1.22
     outwardly
    1.14
    乍
    1.03
    看上去
    1.02
     superficial
    1.00
     apariencia
    0.95
    表面
    0.95
    看似
    0.95
     apparence
    0.93
    Activations Density 0.087%

    No Known Activations