© 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. 97751
    Prev
    Next
    INDEX
    Explanations

    negative descriptions following common auxiliaries

    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
    NoError
    -0.92
    konom
    -0.86
     sain
    -0.86
    heds
    -0.84
    unno
    -0.83
    HasMaxLength
    -0.82
    namental
    -0.82
    SuccessListener
    -0.82
    chio
    -0.79
     defraud
    -0.79
    POSITIVE LOGITS
     poor
    3.31
     terrible
    3.27
     bad
    3.08
     awful
    2.64
    poor
    2.61
     lousy
    2.48
    Poor
    2.45
    terrible
    2.39
    Terrible
    2.34
     horrible
    2.23
    Activations Density 0.108%

    No Known Activations