© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3249
    Prev
    Next
    INDEX
    Explanations

    genocide questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    '
    1.97
    ’
    1.88
     of
    1.82
     period
    1.80
     reveals
    1.73
    しの
    1.72
     which
    1.70
     either
    1.70
     was
    1.69
     came
    1.69
    POSITIVE LOGITS
    LICENSE
    1.85
    7
    1.83
     makeSound
    1.74
     monomers
    1.69
    RIK
    1.64
     monopole
    1.64
    6
    1.61
     LICENSE
    1.60
     mesenchymal
    1.57
     httpServer
    1.52
    Activations Density 0.010%

    No Known Activations