© 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. 212470
    Prev
    Next
    INDEX
    Explanations

    Banana Splits

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

    late delivery or crossed lines

    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
    簡単に
    0.57
    ヤマハ
    0.47
    ダ
    0.45
    您可以
    0.44
    関数
    0.43
     සෑම
    0.43
    ト
    0.43
    場合
    0.43
     fonksiyon
    0.43
     SYM
    0.42
    POSITIVE LOGITS
    elecimento
    0.50
    halla
    0.50
    evich
    0.50
    ares
    0.49
    ien
    0.47
    ickey
    0.47
    itec
    0.47
    pero
    0.47
    ietic
    0.47
    concern
    0.47
    Activations Density 0.000%

    No Known Activations