© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    importing or loading modules

    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
    onov
    0.35
    <0xB7>
    0.28
     writers
    0.27
    ศัพท์
    0.27
    ління
    0.27
    শ্র
    0.26
    writers
    0.26
    𝙮
    0.26
     जिससे
    0.25
     হাসিনার
    0.25
    POSITIVE LOGITS
     train
    0.35
     trace
    0.33
     Train
    0.30
     asset
    0.30
     Trace
    0.29
     geometric
    0.29
    ၜ
    0.29
     lith
    0.29
    trace
    0.29
     keb
    0.28
    Activations Density 0.002%

    No Known Activations