© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78668
    Prev
    Next
    INDEX
    Explanations

    dissolve or disband

    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_34/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
     Unclassified
    -0.77
    cione
    -0.77
    Italie
    -0.76
    arei
    -0.75
     Belinda
    -0.74
     Lightfoot
    -0.74
    vocato
    -0.72
    Ⓨ
    -0.71
     synerg
    -0.71
    AFX
    -0.68
    POSITIVE LOGITS
     dissolve
    5.66
     dissolved
    5.47
     dissolution
    5.44
     dissolving
    5.22
     dissolves
    5.09
    diss
    4.63
     Dissolution
    4.16
    Diss
    4.06
     Dissolve
    3.95
     Dissolved
    3.72
    Activations Density 0.133%

    No Known Activations