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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201321
    Prev
    Next
    INDEX
    Explanations

    required for student

    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
    册
    0.46
    anchez
    0.44
     Católica
    0.43
    的研究
    0.43
     đươ
    0.41
     bih
    0.40
     khiển
    0.40
    Mrs
    0.40
    ्युअल
    0.39
    dostęp
    0.39
    POSITIVE LOGITS
     imprison
    0.53
     weaponry
    0.47
     rDNA
    0.47
    ਹ
    0.46
    𝗹
    0.46
     초기
    0.46
     উদ্ভি
    0.46
     ਲ
    0.46
     weapons
    0.45
    weapons
    0.45
    Activations Density 0.004%

    No Known Activations