© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    programming code explanation

    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
     fashioned
    2.49
    هل
    2.47
     fascinating
    2.40
    𝓻
    2.40
     porous
    2.25
     autres
    2.16
    こんな
    2.15
    otic
    2.11
     hề
    2.11
    인의
    2.09
    POSITIVE LOGITS
    ن
    3.69
    ()=>{
    3.51
    違い
    2.97
    ل
    2.80
    ally
    2.77
    ции
    2.68
    气息
    2.68
    ために
    2.68
    মূলক
    2.64
    ration
    2.63
    Activations Density 0.879%

    No Known Activations