© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34846
    Prev
    Next
    INDEX
    Explanations

    Obsidian Order, Shadow stresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    צוני
    0.47
    மில்லை
    0.44
    ত্তি
    0.43
    隶
    0.42
     BasicContainer
    0.42
    鹛
    0.41
    属于
    0.41
    CharArray
    0.41
    ཱ
    0.41
    듈
    0.41
    POSITIVE LOGITS
     zahlreichen
    0.42
     বারবার
    0.42
    money
    0.41
     मुकाब
    0.41
    資金
    0.41
    各地
    0.41
     últimos
    0.39
     locations
    0.38
    estas
    0.38
    PLAN
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.