© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188838
    Prev
    Next
    INDEX
    Explanations

    `Denmark` `domain`, `tire` `tracking`, `trailer` `deck`

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

    Self-compassion

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unsurprisingly
    0.54
    টে
    0.48
    マップ
    0.48
    ↑
    0.46
    バイ
    0.45
    হান
    0.44
    եկ
    0.44
    Subsequently
    0.44
    ジャー
    0.43
    パワー
    0.43
    POSITIVE LOGITS
    il
    0.50
     TH
    0.49
     restaur
    0.45
     y
    0.44
     Fractional
    0.44
     Doctor
    0.43
     Validity
    0.43
     frances
    0.42
    ることが
    0.42
     French
    0.42
    Activations Density 0.001%

    No Known Activations