© 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. 48106
    Prev
    Next
    INDEX
    Explanations

    logical tautologies and consequences

    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
     CLE
    -0.77
     фран
    -0.73
     Dabei
    -0.71
    €
    -0.71
    watcher
    -0.70
    зай
    -0.68
    stubs
    -0.68
     err
    -0.68
     Binary
    -0.68
     опять
    -0.68
    POSITIVE LOGITS
     tauto
    1.44
     consequences
    1.30
     entailed
    1.25
     consequence
    1.17
     Consequences
    1.11
     conséquence
    1.09
    Consequences
    1.01
     entail
    1.00
     truths
    0.98
     Redund
    0.96
    Activations Density 0.038%

    No Known Activations