© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7202
    Prev
    Next
    INDEX
    Explanations

    truth and honesty

    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_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifient
    0.82
    बंदी
    0.74
    Notify
    0.70
    বারিক
    0.68
     限定
    0.67
    াইলে
    0.66
     ಕ
    0.66
    [@
    0.65
    ান্য
    0.64
     Wert
    0.64
    POSITIVE LOGITS
     truth
    4.96
    truth
    4.38
    Truth
    4.12
     Truth
    4.12
     truths
    3.89
     verità
    3.45
     Wahrheit
    3.34
     verdad
    3.29
    truths
    3.24
     vérité
    3.23
    Activations Density 0.293%

    No Known Activations