© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15092
    Prev
    Next
    INDEX
    Explanations

    flow through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    embedded
    0.59
     położ
    0.57
     embedded
    0.56
    ട്
    0.53
    კი
    0.52
     नस्
    0.50
    planted
    0.50
    植
    0.49
    pis
    0.49
    藏
    0.49
    POSITIVE LOGITS
     flow
    2.38
     flowing
    2.30
     flows
    2.25
     Flow
    2.22
    Flow
    2.06
     Flows
    2.06
     flowed
    2.05
    流
    2.03
     FLOW
    2.02
    flow
    1.98
    Activations Density 0.338%

    No Known Activations