© 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. 115936
    Prev
    Next
    INDEX
    Explanations

    disappear or vanish

    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
     Schulz
    -0.81
     Weakness
    -0.79
     keywords
    -0.79
    diol
    -0.76
     Alexey
    -0.75
    ımı
    -0.73
    determination
    -0.71
    祚
    -0.71
     antworte
    -0.71
    blik
    -0.70
    POSITIVE LOGITS
     disappearance
    3.66
     disappear
    3.47
     disappeared
    3.27
     disappearing
    3.22
     disappears
    2.98
     vanishing
    2.59
     vanish
    2.53
     исчез
    2.42
     desapare
    2.42
     vanished
    2.38
    Activations Density 0.067%

    No Known Activations