© 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. 117433
    Prev
    Next
    INDEX
    Explanations

    dark matter halo models

    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
    Bn
    -0.76
    อด
    -0.75
    ℂ
    -0.73
    работка
    -0.71
    issor
    -0.70
     {:
    -0.68
    nsk
    -0.68
     enamel
    -0.67
    yra
    -0.67
     neighbors
    -0.66
    POSITIVE LOGITS
     Hern
    0.99
    viri
    0.88
    halo
    0.86
     Profiles
    0.84
     profiles
    0.82
     profile
    0.82
     hernia
    0.82
     Zwer
    0.79
     halo
    0.78
     dwarf
    0.78
    Activations Density 0.018%

    No Known Activations