© 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. 213447
    Prev
    Next
    INDEX
    Explanations

    right to choose

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

    return it !

    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
     SDN
    0.46
     سرحد
    0.46
    ፧
    0.46
    atlantic
    0.45
     भंड
    0.44
    兩
    0.44
     पोट
    0.44
     Hacer
    0.44
    𠃍
    0.44
    मैन
    0.43
    POSITIVE LOGITS
     lipids
    0.52
     came
    0.49
     well
    0.47
     grew
    0.47
     laptops
    0.46
     ē
    0.46
     looks
    0.45
     ours
    0.45
    (
    0.45
     our
    0.44
    Activations Density 0.000%

    No Known Activations