© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    questions and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    ل
    0.48
    ル
    0.47
     apparaître
    0.46
    VES
    0.46
    ကျွန်
    0.45
    寘
    0.45
    澶
    0.45
     Inbetriebnahme
    0.44
    제
    0.44
     tume
    0.43
    POSITIVE LOGITS
    backed
    0.49
     ван
    0.48
    marital
    0.48
    judicial
    0.44
    assays
    0.42
    creet
    0.42
     душа
    0.42
    gone
    0.40
    lymph
    0.40
    gué
    0.40
    Activations Density 0.009%

    No Known Activations