© 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. 10-GEMMASCOPE-RES-131K
    7. 44398
    Prev
    Next
    INDEX
    Explanations

    hair color and style

    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
    cobacterium
    -1.22
     materials
    -1.17
     variety
    -1.13
    emb
    -1.10
     relationship
    -1.10
     okreś
    -1.10
     relationships
    -1.09
    ↵
    -1.08
     way
    -1.07
     autre
    -1.05
    POSITIVE LOGITS
    arrings
    1.32
    denk
    1.13
     protože
    1.07
     意思
    1.07
    んでいます
    1.05
     เรา
    1.04
     Kangaroo
    1.04
     overhanging
    1.03
     Mereka
    1.03
     scarves
    1.02
    Activations Density 0.033%

    No Known Activations