© 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. 103877
    Prev
    Next
    INDEX
    Explanations

    cannot be undone

    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
     саду
    -0.91
    bub
    -0.89
     considéré
    -0.88
    wendungs
    -0.88
     افتراض
    -0.87
    épendance
    -0.86
     rapidement
    -0.85
    ް
    -0.84
    pep
    -0.83
    baum
    -0.82
    POSITIVE LOGITS
     know
    1.87
     grasp
    1.86
     understand
    1.63
     knowledge
    1.49
     understanding
    1.38
     apprehend
    1.36
     knowing
    1.32
     penetrate
    1.26
     grasping
    1.23
     access
    1.22
    Activations Density 0.032%

    No Known Activations