© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41440
    Prev
    Next
    INDEX
    Explanations

    Darwin and evolution

    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
     apparaître
    0.52
    Ꮘ
    0.51
    酆
    0.50
    保護
    0.49
    部门
    0.49
    古墳
    0.48
     zostać
    0.48
    ⸨
    0.48
     bezpečnost
    0.47
    ötzlich
    0.47
    POSITIVE LOGITS
     Darwin
    0.61
    Darwin
    0.50
     biodiversity
    0.47
     benthic
    0.40
    darwin
    0.38
     zebrafish
    0.38
    underline
    0.37
     onshore
    0.36
    heap
    0.36
     aero
    0.36
    Activations Density 0.020%

    No Known Activations