© 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. 64554
    Prev
    Next
    INDEX
    Explanations

    existential quantifiers or variables

    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
     habits
    -1.40
     Habits
    -1.15
     habit
    -1.05
     hábitos
    -1.01
    habit
    -0.88
    习惯
    -0.88
    習慣
    -0.84
     Habit
    -0.82
    Habit
    -0.79
     habitudes
    -0.79
    POSITIVE LOGITS
     successor
    1.03
     Nat
    0.98
    Nat
    0.94
     succeeded
    0.93
     succ
    0.93
     numerals
    0.89
     Success
    0.88
    Succ
    0.85
     nat
    0.82
    successor
    0.82
    Activations Density 0.046%

    No Known Activations