© 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. 130344
    Prev
    Next
    INDEX
    Explanations

    is known or credited

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

    past states and events

    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
    President
    0.46
     ಹೊಸ
    0.43
     νέ
    0.42
    Apparently
    0.41
    Созда
    0.41
    每年
    0.40
    ুরুর
    0.40
    工事
    0.40
    RZ
    0.40
    ፖ
    0.40
    POSITIVE LOGITS
     credited
    0.48
     intervalo
    0.45
     descript
    0.44
     opis
    0.43
     recollection
    0.41
     वर्णित
    0.41
     débit
    0.41
    credited
    0.41
     Kabir
    0.41
     descrito
    0.41
    Activations Density 0.059%

    No Known Activations