© 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. 16487
    Prev
    Next
    INDEX
    Explanations

    destruction, damage, decay

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

    deterioration and decay

    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
    ڈنگ
    0.49
     ট্রেনিং
    0.48
    ထုတ်
    0.47
     cured
    0.47
     ટુ
    0.46
     ވަ
    0.45
     ValidationError
    0.45
     已
    0.44
     Practitioner
    0.44
     subdued
    0.44
    POSITIVE LOGITS
     разру
    1.20
     destruction
    1.09
    破壊
    1.09
     destru
    1.07
     destrucción
    1.05
     destroy
    1.03
    毁
    1.03
    destroy
    0.98
     destruir
    0.98
     Destroy
    0.98
    Activations Density 0.084%

    No Known Activations