© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117944
    Prev
    Next
    INDEX
    Explanations

    checks for equality or truthfulness

    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
    False
    -1.80
     False
    -1.65
    FALSE
    -1.55
     FALSE
    -1.52
    Nope
    -1.47
     off
    -1.40
    assertFalse
    -1.38
     false
    -1.37
    false
    -1.34
    off
    -1.24
    POSITIVE LOGITS
     true
    3.22
     True
    2.09
    true
    1.91
     TRUE
    1.80
    TRUE
    1.54
    True
    1.46
     verdade
    1.39
     правда
    1.39
     yes
    1.37
     truth
    1.31
    Activations Density 0.034%

    No Known Activations