© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2537
    Prev
    Next
    INDEX
    Explanations

    I see or you see

    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
     therefore
    -0.95
     Gehir
    -0.93
     Ministério
    -0.92
    𝕕
    -0.91
    ığın
    -0.86
     schim
    -0.81
     Senhor
    -0.80
    ጫ
    -0.80
    unconfirmed
    -0.79
    欄
    -0.79
    POSITIVE LOGITS
     objectMapper
    0.86
     frente
    0.85
    ould
    0.84
    ise
    0.82
     gospodar
    0.80
    sett
    0.79
    unis
    0.79
    curl
    0.77
     zwanzig
    0.76
    sedown
    0.75
    Activations Density 0.011%

    No Known Activations