© 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. 109490
    Prev
    Next
    INDEX
    Explanations

    preventing negative outcomes

    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
    ONIA
    -0.88
     légèrement
    -0.87
    お風呂
    -0.84
     ſol
    -0.83
    Decay
    -0.82
     Künst
    -0.82
    Descriere
    -0.81
     сигнал
    -0.81
     prode
    -0.80
    zado
    -0.79
    POSITIVE LOGITS
     premature
    1.20
     excessive
    1.16
     undesirable
    1.09
     excessively
    1.05
     problems
    1.03
     undes
    1.03
     damage
    0.96
    undes
    0.94
     unwanted
    0.89
     damaging
    0.89
    Activations Density 0.165%

    No Known Activations