© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 1854
    Prev
    Next
    INDEX
    Explanations

    truth and falsehood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     কাতর
    0.73
     Brows
    0.71
    itié
    0.69
    Browsable
    0.64
    Tokens
    0.63
     ώ
    0.63
    ൺലൈ
    0.61
    逡
    0.60
    ಿಸ
    0.60
    морфи
    0.60
    POSITIVE LOGITS
     false
    3.26
     truth
    3.07
     untrue
    3.02
     inaccurate
    2.97
    false
    2.97
     falsehood
    2.97
     False
    2.92
     FALSE
    2.83
    False
    2.83
    truth
    2.78
    Activations Density 1.573%

    No Known Activations