© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3571
    Prev
    Next
    INDEX
    Explanations

    divisive and controversial topics

    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
     appBar
    0.71
     बलात्कार
    0.66
     стомато
    0.63
     শাস্তি
    0.63
    MyAdmin
    0.62
     steals
    0.61
     steal
    0.61
    꿇
    0.59
     Buildable
    0.59
     বিদ্যা
    0.59
    POSITIVE LOGITS
     polarization
    2.34
     polarized
    2.30
     polarisation
    2.11
     polarised
    2.10
     polar
    2.10
     divides
    2.08
     polarizing
    2.04
     divisions
    2.04
     divide
    2.01
     Polarization
    1.98
    Activations Density 0.245%

    No Known Activations