© 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. 22-GEMMASCOPE-RES-131K
    7. 26821
    Prev
    Next
    INDEX
    Explanations

    falsehoods and misrepresentations

    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_22/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
    UNIDENTIFIED
    -0.90
    այի
    -0.88
    Losing
    -0.86
    Lost
    -0.85
     αὐ
    -0.85
     diesen
    -0.85
    Puck
    -0.84
     anbieten
    -0.83
     τῶν
    -0.82
    ׇ
    -0.81
    POSITIVE LOGITS
    false
    1.35
     false
    1.34
    False
    1.20
     concealment
    1.20
    assertFalse
    1.17
     about
    1.15
     False
    1.14
     misleading
    1.09
     lied
    1.09
     concealing
    1.08
    Activations Density 0.037%

    No Known Activations