© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8299
    Prev
    Next
    INDEX
    Explanations

    total

    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_22_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
     tím
    0.95
     lowland
    0.86
    全体
    0.84
     되겠
    0.84
     тому
    0.83
     trate
    0.82
    整個
    0.81
    т
    0.80
     ст
    0.80
     stagger
    0.78
    POSITIVE LOGITS
     मिलाकर
    1.93
    izadores
    1.58
    Energ
    1.43
    itarian
    1.34
    izing
    1.32
    మీ
    1.29
    izando
    1.29
     aantal
    1.23
    ামুটি
    1.23
     parenteral
    1.21
    Activations Density 0.053%

    No Known Activations