© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66509
    Prev
    Next
    INDEX
    Explanations

    Russian grammar cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -2.48
     \
    -2.30
     französische
    -2.19
     or
    -2.19
    还真是
    -2.16
    0
    -2.16
     letzte
    -2.09
     y
    -2.06
    两位
    -2.06
     breite
    -2.03
    POSITIVE LOGITS
    呴
    2.72
    푆
    2.69
    媗
    2.59
    ꙮ
    2.52
    
    2.47
    ⮑
    2.44
     όταν
    2.42
    푉
    2.42
    these
    2.42
    have
    2.42
    Activations Density 0.004%

    No Known Activations