© 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. 49489
    Prev
    Next
    INDEX
    Explanations

    ermine; adult children

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

    project thesis results

    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
    淺
    0.52
    𝔬
    0.52
    دف
    0.51
    计划
    0.49
    僅
    0.47
    тук
    0.47
    計劃
    0.46
    🖌
    0.46
     سائ
    0.46
    テーション
    0.45
    POSITIVE LOGITS
    Bass
    0.54
    Pon
    0.53
    Sang
    0.51
    Lopez
    0.50
    bass
    0.50
    Iw
    0.50
    Shaw
    0.49
    voice
    0.47
     Pon
    0.47
    ill
    0.47
    Activations Density 0.000%

    No Known Activations