© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75729
    Prev
    Next
    INDEX
    Explanations

    api version identifiers

    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
    RESTRICT
    -0.90
    rası
    -0.89
    prende
    -0.86
     Kamu
    -0.84
    Veget
    -0.84
     frequently
    -0.84
    iphery
    -0.83
    AKO
    -0.83
     usually
    -0.82
     dirigez
    -0.82
    POSITIVE LOGITS
    2
    0.98
    inare
    0.92
    赶紧
    0.92
    了一個
    0.91
    uckles
    0.90
    を注文
    0.89
    gerichte
    0.88
     tion
    0.87
    最新
    0.85
    vielen
    0.85
    Activations Density 0.035%

    No Known Activations