© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4929
    Prev
    Next
    INDEX
    Explanations

    entities that do or have

    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_29_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
     dala
    0.51
    Returned
    0.51
    шед
    0.50
     בד
    0.49
     bantuan
    0.49
     דו
    0.48
     обращения
    0.48
     た
    0.47
     Leveraging
    0.46
    obtained
    0.46
    POSITIVE LOGITS
     overheat
    0.84
     compete
    0.83
     circulate
    0.80
     oxidize
    0.80
     regenerate
    0.79
     starve
    0.78
     rotate
    0.78
     develop
    0.77
     radiate
    0.76
     vanish
    0.76
    Activations Density 0.336%

    No Known Activations