© 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. 39635
    Prev
    Next
    INDEX
    Explanations

    array indexing and subscripts

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

    accessing elements using numerical indices

    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
    HP
    0.47
    hoon
    0.43
    پول
    0.42
    劑
    0.42
    Hp
    0.41
    導演
    0.41
     úč
    0.41
     hp
    0.41
     evacu
    0.40
    समा
    0.40
    POSITIVE LOGITS
    下标
    0.69
    indices
    0.66
     indexing
    0.66
     Indices
    0.64
     indices
    0.61
    Indices
    0.61
    indexing
    0.61
    索引
    0.58
     indexes
    0.57
    getIndex
    0.56
    Activations Density 0.003%

    No Known Activations