© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75906
    Prev
    Next
    INDEX
    Explanations

    also, when, if, while

    np_acts-logits-general · gemini-2.5-flash-lite

    definitions, examples, or scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     管
    0.40
    াজ
    0.36
    LING
    0.36
    ଣ୍
    0.35
    intersects
    0.35
     realignment
    0.33
    熬
    0.33
    ;,
    0.32
    াবের
    0.32
    ாண்ட
    0.32
    POSITIVE LOGITS
     Bhosle
    0.42
    
    0.37
     Вас
    0.37
    »:
    0.36
    ject
    0.35
     заклю
    0.35
     zusätzlich
    0.35
    зже
    0.35
    疵
    0.35
    ursed
    0.34
    Activations Density 0.269%

    No Known Activations