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

    Neuronpedia

    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. 70863
    Prev
    Next
    INDEX
    Explanations

    say we're

    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_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
    chets
    0.42
    【
    0.42
    UserProfile
    0.39
     दृष्टिकोण
    0.39
    uem
    0.38
     【
    0.38
    邹
    0.38
    ITU
    0.38
    User
    0.37
    논
    0.37
    POSITIVE LOGITS
     aloft
    0.49
     veya
    0.48
    গ্র
    0.48
     agré
    0.47
    ิร์
    0.46
     มั้ย
    0.45
    uhà
    0.44
    વ
    0.44
     animale
    0.43
    ર્
    0.43
    Activations Density 0.011%

    No Known Activations