© 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. 65557
    Prev
    Next
    INDEX
    Explanations

    multipart and multimedia

    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
     โดย
    -0.94
    してくれた
    -0.88
    ὦ
    -0.81
     inspec
    -0.79
    unea
    -0.79
     impossibility
    -0.77
    くれた
    -0.77
     folhe
    -0.76
     distur
    -0.73
    vinte
    -0.73
    POSITIVE LOGITS
     Multi
    1.03
    MULT
    1.02
    Multi
    0.98
     multi
    0.96
    ו
    0.91
    Ѕ
    0.91
     件
    0.91
    multi
    0.89
    mul
    0.88
    เส
    0.88
    Activations Density 0.010%

    No Known Activations