© 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. 111041
    Prev
    Next
    INDEX
    Explanations

    authorized access

    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
    ”،
    -0.79
    Roads
    -0.79
     operational
    -0.76
    ジー
    -0.73
    してみた
    -0.73
     tra
    -0.73
    теру
    -0.73
     hayan
    -0.72
     décide
    -0.71
    Ա
    -0.71
    POSITIVE LOGITS
    щность
    0.81
    ḫ
    0.80
     volando
    0.78
    ोध
    0.77
     july
    0.76
     Tá
    0.75
     wl
    0.75
     overlapped
    0.75
     Frida
    0.75
    辞典
    0.75
    Activations Density 0.025%

    No Known Activations