© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8707
    Prev
    Next
    INDEX
    Explanations

    rules and politeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     toxicity
    0.76
     poisoning
    0.69
    锤
    0.69
     రైతు
    0.68
    獄
    0.67
    毒
    0.66
     toxic
    0.65
     treo
    0.64
     yük
    0.64
     worry
    0.64
    POSITIVE LOGITS
     disrespectful
    0.88
     reclining
    0.82
     sagittal
    0.81
    ख्ती
    0.81
     desec
    0.81
    灘
    0.79
     Displays
    0.77
     widescreen
    0.76
    廸
    0.76
    觐
    0.76
    Activations Density 0.158%

    No Known Activations