© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134103
    Prev
    Next
    INDEX
    Explanations

    data processing pipelines

    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_40_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
    OTTOM
    0.40
     რამდენ
    0.38
     말미
    0.38
     tome
    0.38
    ポケット
    0.38
    斯拉
    0.38
     몇
    0.37
    ETERS
    0.37
     ሥ
    0.37
     niekoľ
    0.37
    POSITIVE LOGITS
     değildir
    0.47
    alert
    0.44
     развития
    0.41
     =
    0.40
     செய்தி
    0.38
     alerts
    0.38
    rust
    0.38
    ung
    0.37
     alert
    0.37
    명
    0.36
    Activations Density 0.002%

    No Known Activations