© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54884
    Prev
    Next
    INDEX
    Explanations

    meeting minutes and approvals

    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_31_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
     puissent
    0.53
     çöze
    0.43
    <unused635>
    0.43
     puisse
    0.42
     chciał
    0.42
    deload
    0.42
     новий
    0.42
    ୫
    0.42
    縷
    0.41
     पाँच
    0.41
    POSITIVE LOGITS
    通过
    0.50
    作为
    0.49
    Kotlin
    0.48
     cavities
    0.47
    Blob
    0.44
     blobs
    0.44
    Cave
    0.43
    G
    0.43
    Children
    0.43
    是一个
    0.42
    Activations Density 0.007%

    No Known Activations