© 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. 110364
    Prev
    Next
    INDEX
    Explanations

    committed suicide, goal setter

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

    further refinement

    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
    '.
    0.46
    .'
    0.44
    ми
    0.43
     fortuit
    0.41
     invariance
    0.41
    *
    0.40
    지
    0.40
    gette
    0.40
    ジ
    0.40
    ohn
    0.40
    POSITIVE LOGITS
    SwapChain
    0.52
     ceramics
    0.50
     eucalyptus
    0.49
     Strateg
    0.49
    সময়
    0.49
     đạp
    0.48
    陶瓷
    0.48
     Ceramics
    0.48
     দক্ষিণে
    0.47
     ubicación
    0.47
    Activations Density 0.001%

    No Known Activations