© 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. 13004
    Prev
    Next
    INDEX
    Explanations

    nature and wildlife

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

    nature and the natural world

    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
     poslov
    0.58
    评标
    0.55
     biznes
    0.54
     финансо
    0.53
     GDPR
    0.52
     beruf
    0.51
    訕
    0.51
     ገን
    0.50
     algebraically
    0.50
     salaried
    0.50
    POSITIVE LOGITS
     wildlife
    1.47
     naturalist
    1.45
     природ
    1.39
     Nature
    1.38
     Wildlife
    1.38
    Nature
    1.36
     ప్రకృతి
    1.35
     প্রকৃতির
    1.30
    Wildlife
    1.29
     природных
    1.29
    Activations Density 0.236%

    No Known Activations