© 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. 2070
    Prev
    Next
    INDEX
    Explanations

    goes directly against

    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
     Parmi
    0.75
    ப்த
    0.70
     Gibb
    0.69
    ᅬ
    0.67
     टॉपर
    0.67
    írez
    0.66
     Kamm
    0.66
    埙
    0.66
     inz
    0.65
    쁘
    0.65
    POSITIVE LOGITS
     against
    0.98
     Against
    0.92
    Against
    0.88
    against
    0.87
     tegen
    0.83
     gegen
    0.79
     AGAINST
    0.78
     против
    0.77
     counter
    0.76
    Counter
    0.75
    Activations Density 0.160%

    No Known Activations