© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15522
    Prev
    Next
    INDEX
    Explanations

    pleading for peace

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

    softening alternatives or contrasts

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

    conflict and decision-making

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    forgiveness

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
     bolder
    0.52
     반지
    0.46
     boldness
    0.45
    孖
    0.45
     υ
    0.42
     Perkin
    0.41
     掛
    0.41
    强烈
    0.40
    력
    0.40
     movimientos
    0.40
    POSITIVE LOGITS
     forgiveness
    1.09
     forgiving
    1.02
     forgive
    0.99
     forgiven
    0.91
     peacefully
    0.91
     softened
    0.91
     amicable
    0.89
     concili
    0.88
     soften
    0.86
     peaceful
    0.84
    Activations Density 0.588%

    No Known Activations