© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46709
    Prev
    Next
    INDEX
    Explanations

    project, shortcuts, mutual, mine

    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_16_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
    ត្រូ
    0.60
     spezi
    0.58
    រស
    0.55
     Nutzen
    0.54
    ឈ្ម
    0.53
     Inoltre
    0.52
     esimerk
    0.52
    茨
    0.52
    luit
    0.50
     Arzt
    0.50
    POSITIVE LOGITS
     lengua
    0.55
    EN
    0.54
    worked
    0.53
    گذاری
    0.52
     kết
    0.52
     be
    0.51
     사이에
    0.50
    지
    0.50
    ۹
    0.50
     것이
    0.50
    Activations Density 0.000%

    No Known Activations