© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 30959
    Prev
    Next
    INDEX
    Explanations

    NLP tasks

    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
     &.
    0.57
     ah
    0.56
     vett
    0.56
    屌
    0.55
     adjuster
    0.53
     白色
    0.51
     Zain
    0.49
     嗯
    0.49
     mathematic
    0.49
     kinda
    0.49
    POSITIVE LOGITS
     synthesis
    0.52
    ஸ்ட்
    0.50
    <td>
    0.49
    =
    0.48
     Interactions
    0.48
     iconic
    0.47
    Instructions
    0.47
    #
    0.46
     Synthesis
    0.45
     следующий
    0.45
    Activations Density 0.550%

    No Known Activations