© 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. 40-GEMMASCOPE-2-RES-65K
    7. 848
    Prev
    Next
    INDEX
    Explanations

    javascript code declaration

    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_40_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
    Trajectories
    0.36
    ัพท์
    0.36
    媾
    0.36
    ्यूड
    0.34
    ᑯ
    0.34
    িল্প
    0.34
    лке
    0.34
    بري
    0.34
    ╽
    0.34
    ECK
    0.33
    POSITIVE LOGITS
    const
    0.40
     Poker
    0.38
     />
    0.38
     const
    0.38
    af
    0.36
    console
    0.35
     times
    0.35
    times
    0.34
    …
    0.34
    async
    0.34
    Activations Density 0.086%

    No Known Activations