© 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. 81690
    Prev
    Next
    INDEX
    Explanations

    grapeseed oil and toxins

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

    find words

    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
     Volumen
    0.49
     volumen
    0.47
    鵬
    0.42
     centroid
    0.41
     Defin
    0.41
     condenser
    0.41
    𝗳
    0.40
    㖑
    0.40
    کم
    0.40
    ボリューム
    0.40
    POSITIVE LOGITS
     youll
    0.49
    igur
    0.44
     inté
    0.43
     неда
    0.43
    ለመ
    0.43
     lâm
    0.42
     dünyaya
    0.42
    iqui
    0.42
     imgSrc
    0.41
    你有
    0.40
    Activations Density 0.000%

    No Known Activations