© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91603
    Prev
    Next
    INDEX
    Explanations

    drum machine sounds

    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
     Virtual
    -0.82
     Universal
    -0.80
     Social
    -0.80
    ύ
    -0.77
    kelt
    -0.74
    fø
    -0.74
     合
    -0.72
     Online
    -0.72
     Green
    -0.71
    Online
    -0.71
    POSITIVE LOGITS
     PATTERN
    0.88
    igshid
    0.87
     trig
    0.77
    coff
    0.77
    прода
    0.77
    ⃕
    0.75
    MessageDigest
    0.75
     nematodes
    0.75
    
    0.75
     participantes
    0.74
    Activations Density 0.005%

    No Known Activations