© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8764
    Prev
    Next
    INDEX
    Explanations

    declarations of string variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    0.82
    ার
    0.78
     betterment
    0.65
    𝚕
    0.65
    ITECTURE
    0.63
    ل
    0.61
    𝚝
    0.59
     ""){
    0.59
    +}^{
    0.59
    ய்ப்ப
    0.58
    POSITIVE LOGITS
     ern
    0.66
    مة
    0.58
    AP
    0.58
     অর্থনৈতিক
    0.56
    Сред
    0.55
    妻
    0.55
     ideological
    0.54
     économ
    0.53
    ES
    0.53
     东
    0.53
    Activations Density 0.256%

    No Known Activations