© 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. 101050
    Prev
    Next
    INDEX
    Explanations

    words starting with morph

    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
    訁
    -2.97
    蕺
    -2.80
    鸲
    -2.77
    
    -2.63
    蟥
    -2.52
    缡
    -2.50
     stap
    -2.38
     asesin
    -2.36
    
    -2.33
     liet
    -2.31
    POSITIVE LOGITS
    Y
    3.02
    K
    2.91
    </td>
    2.80
    O
    2.41
     heiß
    2.17
    但我
    2.14
     beeind
    2.14
    X
    2.13
     стали
    2.13
     desiring
    2.11
    Activations Density 0.010%

    No Known Activations