© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47960
    Prev
    Next
    INDEX
    Explanations

    acts of rescue and heroism

    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/layer_31_width_262k_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
    烦
    0.48
    ರಿಸಿ
    0.41
     हिन्द
    0.41
     ори
    0.40
    ఆ
    0.40
    磋
    0.40
    ворю
    0.39
     ponemos
    0.39
     फरक
    0.38
    
    0.38
    POSITIVE LOGITS
     rescuing
    0.87
     rescue
    0.79
     rescued
    0.74
     rescues
    0.70
     heroism
    0.69
     heroic
    0.68
     saving
    0.67
     hero
    0.64
    救
    0.64
    rescue
    0.62
    Activations Density 0.013%

    No Known Activations