© 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. 31107
    Prev
    Next
    INDEX
    Explanations

    child and parent relationships

    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
     sneered
    -0.88
     Bajos
    -0.84
    parti
    -0.81
    伅
    -0.79
     füllen
    -0.78
    apro
    -0.77
     Passive
    -0.75
     Kaffee
    -0.75
    Passive
    -0.74
     melons
    -0.73
    POSITIVE LOGITS
     little
    1.20
    little
    0.97
    Little
    0.92
     kleinen
    0.91
     adults
    0.91
    儼
    0.89
    льної
    0.88
    ÍAS
    0.88
     childish
    0.85
     Little
    0.83
    Activations Density 0.003%

    No Known Activations