© 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. 9220
    Prev
    Next
    INDEX
    Explanations

    Speech indicators

    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
     methylation
    1.38
    
    1.31
     inequities
    1.30
     Additionally
    1.29
     Coming
    1.26
    ત
    1.26
     Because
    1.24
     arterioles
    1.19
     getView
    1.19
     During
    1.19
    POSITIVE LOGITS
    kenalkan
    1.18
    iya
    1.07
    ை
    1.07
    is
    1.05
    y
    1.03
    Ҳ
    1.02
    utor
    1.01
    िक
    1.01
    iswa
    1.00
    oje
    1.00
    Activations Density 0.372%

    No Known Activations