© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48877
    Prev
    Next
    INDEX
    Explanations

    Sardar, Sergeant, Sard

    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
     grade
    -0.81
    gcm
    -0.77
    harf
    -0.76
    됩
    -0.75
     alta
    -0.74
     モン
    -0.74
     hoje
    -0.73
    скі
    -0.72
    argb
    -0.72
    珍珠
    -0.72
    POSITIVE LOGITS
    eaf
    0.71
    キャン
    0.68
     冊
    0.67
     убий
    0.65
    cierge
    0.65
     major
    0.65
    ماعة
    0.65
    Assured
    0.65
    NAH
    0.64
    dsp
    0.63
    Activations Density 0.027%

    No Known Activations