© 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. 118950
    Prev
    Next
    INDEX
    Explanations

    official actions and figures

    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
    燔
    0.48
     Chip
    0.42
    کرین
    0.42
     Calculated
    0.41
    চ্যুত
    0.41
    Chip
    0.40
    绩效
    0.40
    లోకి
    0.39
    婼
    0.39
    garakan
    0.39
    POSITIVE LOGITS
    亲自
    0.46
     comrade
    0.45
    谆
    0.41
     comrades
    0.41
     ~
    0.40
     Comrade
    0.39
     explicitly
    0.39
     发表
    0.39
    指出
    0.38
    gener
    0.38
    Activations Density 0.004%

    No Known Activations