© 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. 106625
    Prev
    Next
    INDEX
    Explanations

    honest, honesty, dishonest

    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
     occupé
    -0.93
     herunterladen
    -0.88
    ...........
    -0.86
     formally
    -0.85
     única
    -0.85
    sessionStorage
    -0.84
     consentimento
    -0.83
     réel
    -0.83
    assertThrows
    -0.82
    IAction
    -0.82
    POSITIVE LOGITS
     honest
    1.83
     Honest
    1.76
    honest
    1.61
    Honest
    1.59
     HON
    1.44
     assessment
    1.31
     appraisal
    1.25
     assessments
    1.24
     honesty
    1.13
     sincere
    1.11
    Activations Density 0.010%

    No Known Activations