© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 759
    Prev
    Next
    INDEX
    Explanations

    discussions or explanations of complex topics in simple terms.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    it's not a

    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_65k_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
     usages
    0.18
     コン
    0.18
     consonants
    0.17
     executable
    0.17
     optimizes
    0.15
     eosin
    0.15
     arteries
    0.15
    ；
    0.15
     scaffolds
    0.15
     alanine
    0.15
    POSITIVE LOGITS
     memang
    0.18
     certamente
    0.17
     indeed
    0.17
    pesar
    0.17
    indeed
    0.17
     сожалению
    0.17
    Indeed
    0.16
    amazing
    0.16
    especially
    0.16
    確かに
    0.16
    Activations Density 0.699%

    No Known Activations