© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5852
    Prev
    Next
    INDEX
    Explanations

    expertise, topic, family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     saja
    0.58
     además
    0.57
     außerdem
    0.56
    <unused2197>
    0.55
     It
    0.55
     alone
    0.55
    မူ
    0.55
    как
    0.54
     even
    0.54
    Ultimately
    0.53
    POSITIVE LOGITS
    。
    1.26
     becomes
    1.09
     provides
    1.05
     gets
    1.02
     lends
    1.02
     gives
    1.02
     brings
    1.01
     evokes
    1.01
    ।
    1.00
     has
    0.98
    Activations Density 0.132%

    No Known Activations