© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2064
    Prev
    Next
    INDEX
    Explanations

    json payloads containing specific fields and values.

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

    numbers and specific words

    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
    .
    0.38
     this
    0.34
     by
    0.32
     for
    0.32
     to
    0.32
    ley
    0.32
     as
    0.31
    es
    0.31
    by
    0.29
    ,
    0.29
    POSITIVE LOGITS
     különböző
    0.32
    Mathematical
    0.27
     implementação
    0.27
    罗马
    0.26
     numériques
    0.25
     realizará
    0.25
    스타그램
    0.25
     algéb
    0.25
    Tarefa
    0.25
    碐
    0.25
    Activations Density 0.812%

    No Known Activations