© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5021
    Prev
    Next
    INDEX
    Explanations

    purpose of a tool or scientist

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

    key conceptual nouns—especially abstract, role-defining, or tool/agent terms—within explanatory or technical discourse.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    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
     complicado
    0.21
    E
    0.21
     uitvo
    0.20
     C
    0.20
     verke
    0.19
     the
    0.19
     compi
    0.18
    C
    0.18
     nombre
    0.18
    เป็นการ
    0.18
    POSITIVE LOGITS
     फॉर
    0.30
     for
    0.29
     помога
    0.26
     পরিণত
    0.26
     برای
    0.26
     предоставля
    0.26
     для
    0.26
     потребности
    0.25
     benefiting
    0.25
     extraordinaire
    0.25
    Activations Density 0.472%

    No Known Activations