© 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. 209925
    Prev
    Next
    INDEX
    Explanations

    content understanding

    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
     menyes
    0.38
     각종
    0.38
    ንዳ
    0.37
    letta
    0.36
    専門
    0.36
    ienna
    0.36
    抖
    0.35
    Monty
    0.35
    🜨
    0.35
    жнему
    0.35
    POSITIVE LOGITS
     MLC
    0.43
     Publisher
    0.42
     SVP
    0.41
     EVP
    0.41
    部长
    0.40
     UITableViewCell
    0.40
     لكم
    0.40
    ッケージ
    0.40
     HSBC
    0.40
     அப்போது
    0.39
    Activations Density 0.101%

    No Known Activations