© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24369
    Prev
    Next
    INDEX
    Explanations

    condemn, convicted, condemnation, conviction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     महार
    0.42
    绕
    0.40
     INTERACTIONS
    0.39
     Investigator
    0.39
     disappearing
    0.38
    滃
    0.38
    蓍
    0.38
     প্রতিরোধের
    0.38
    见面
    0.38
    搽
    0.38
    POSITIVE LOGITS
     condemned
    2.08
     conden
    2.02
     condam
    2.02
     condemn
    1.98
     convicted
    1.94
     condemnation
    1.92
     condemning
    1.82
     condemns
    1.74
     condem
    1.72
     conviction
    1.69
    Activations Density 0.002%

    No Known Activations