© 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. 80725
    Prev
    Next
    INDEX
    Explanations

    fall to the wayside

    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
     StringTokenizer
    -0.79
     NSCoder
    -0.79
    thor
    -0.75
    了一下
    -0.66
    acea
    -0.65
     qualifying
    -0.63
     platter
    -0.63
    lobal
    -0.63
    edded
    -0.63
    ridor
    -0.63
    POSITIVE LOGITS
     delusion
    0.72
     Shoes
    0.69
     callback
    0.69
    Ih
    0.68
    SendMessage
    0.68
     装饰
    0.67
    副
    0.67
    dienst
    0.66
    quilo
    0.66
    ꯂ
    0.65
    Activations Density 0.033%

    No Known Activations