© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4187
    Prev
    Next
    INDEX
    Explanations

    charges and severe penalties

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ilegal
    0.72
     legality
    0.71
    dart
    0.71
    डू
    0.70
     ospiti
    0.69
     disputes
    0.68
     crises
    0.68
    ﹗
    0.68
     dientes
    0.68
    బ
    0.67
    POSITIVE LOGITS
     charges
    1.55
     charge
    1.49
    Charge
    1.38
     Charges
    1.37
    charges
    1.36
    charge
    1.32
     Charge
    1.32
    Charges
    1.28
     charged
    1.21
    CHARGE
    1.12
    Activations Density 0.108%

    No Known Activations