© 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. 162905
    Prev
    Next
    INDEX
    Explanations

    renting dumpsters for trash

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

    formatting elements followed by text

    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
    ){
    0.46
    lord
    0.43
     Predicting
    0.43
    brace
    0.42
    lj
    0.42
     INFORMATION
    0.42
    hereafter
    0.41
    ）
    0.41
    LY
    0.41
     Cual
    0.41
    POSITIVE LOGITS
     ecológica
    0.52
     enerji
    0.49
    を超える
    0.49
     reuni
    0.47
    সই
    0.47
     ecol
    0.47
     эко
    0.46
     kecepatan
    0.45
    erasan
    0.45
    ختی
    0.45
    Activations Density 0.002%

    No Known Activations