© 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. 83868
    Prev
    Next
    INDEX
    Explanations

    alpha relaxation

    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
     Curiosity
    -0.77
    投
    -0.75
     GameState
    -0.74
    gawa
    -0.72
    Vene
    -0.71
     Knives
    -0.71
    ষ্
    -0.70
    istu
    -0.69
    Aix
    -0.69
     pregnancies
    -0.69
    POSITIVE LOGITS
     relaxation
    1.75
     relax
    1.63
     Relaxation
    1.45
    relax
    1.40
     Relax
    1.34
     relaj
    1.24
    Relax
    1.19
     Cole
    1.09
     hopping
    1.09
     relaxes
    1.06
    Activations Density 0.049%

    No Known Activations