© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to procedural instructions or guidelines.

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

    then, following, however

    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
     arbitrage
    0.43
    ﻤ
    0.41
     oder
    0.40
     overtly
    0.39
     idols
    0.39
     أو
    0.39
     settlements
    0.39
    ਜ
    0.39
     battles
    0.39
     scape
    0.38
    POSITIVE LOGITS
    Luego
    0.47
     następnie
    0.45
     HOWEVER
    0.44
     Kemudian
    0.44
     இதையடுத்து
    0.44
    然后在
    0.43
     প্রথমে
    0.42
    Then
    0.41
    然后
    0.41
     Normally
    0.40
    Activations Density 0.408%

    No Known Activations