© 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. 57128
    Prev
    Next
    INDEX
    Explanations

    destiny, destined, destination

    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
     merve
    -0.75
     Chairman
    -0.73
     控
    -0.72
    ervor
    -0.70
    กล่าว
    -0.70
     ი
    -0.69
    ХОД
    -0.68
    ɕ
    -0.68
    ℭ
    -0.66
     procurement
    -0.66
    POSITIVE LOGITS
     Destiny
    1.16
     destiny
    1.09
     Dest
    1.07
     DEST
    0.96
    Destiny
    0.96
    dest
    0.90
    Dest
    0.88
    Fö
    0.87
     Destin
    0.85
     destined
    0.79
    Activations Density 0.013%

    No Known Activations