© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22018
    Prev
    Next
    INDEX
    Explanations

    embed content or widgets

    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
     φωτο
    0.46
     세율
    0.40
    setOnAction
    0.40
     फर्श
    0.39
     artériel
    0.39
    ىسى
    0.38
    Personensuche
    0.38
    𒊕
    0.38
    滌
    0.38
     বিশেষণ
    0.38
    POSITIVE LOGITS
     embed
    2.53
     embedding
    2.42
     Embed
    2.34
     embeds
    2.31
    Embed
    2.23
    embed
    2.20
     Embedding
    2.17
     embedded
    2.14
    嵌入
    2.14
    Embedding
    1.98
    Activations Density 0.011%

    No Known Activations