© 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. 98884
    Prev
    Next
    INDEX
    Explanations

    wave functions and states

    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
     blacksmith
    -0.76
    ężczy
    -0.75
     столо
    -0.72
    jec
    -0.71
     Cleveland
    -0.70
     enfrenta
    -0.70
    œurs
    -0.69
     refugees
    -0.69
     Gabel
    -0.68
     DDT
    -0.66
    POSITIVE LOGITS
     wave
    2.41
     Wave
    1.91
    Psi
    1.90
    wave
    1.88
    Wave
    1.84
    psi
    1.83
    Ψ
    1.70
     psi
    1.68
    WAVE
    1.62
     state
    1.53
    Activations Density 0.044%

    No Known Activations