© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1335
    Prev
    Next
    INDEX
    Explanations

    making false claims intentionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repulsion
    0.75
     frowned
    0.72
    unpack
    0.72
     tackles
    0.71
     tackle
    0.71
     zroz
    0.71
    呯
    0.70
     italics
    0.70
    谴
    0.70
     tackling
    0.70
    POSITIVE LOGITS
     fraudulently
    1.55
     unlawfully
    1.53
     knowingly
    1.44
     misled
    1.43
     mislead
    1.40
     deceived
    1.39
     deceive
    1.35
     illegally
    1.34
     defra
    1.34
     allegedly
    1.34
    Activations Density 0.701%

    No Known Activations