© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211062
    Prev
    Next
    INDEX
    Explanations

    mindfulness and kindness

    np_acts-logits-general · gemini-2.5-flash-lite

    sharing ideas or perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    þ
    0.47
     dominating
    0.45
    }[
    0.45
     dominates
    0.45
    ouard
    0.44
    y
    0.44
     accompanied
    0.43
    rs
    0.41
     DNS
    0.40
    svm
    0.40
    POSITIVE LOGITS
     Interfaith
    0.53
    Ⲓ
    0.51
     Kindness
    0.51
     salón
    0.48
    嬅
    0.46
     mindfulness
    0.45
    ‌ന
    0.45
    ราะห์
    0.44
     habitudes
    0.43
     Mindfulness
    0.43
    Activations Density 0.000%

    No Known Activations