© 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. 8817
    Prev
    Next
    INDEX
    Explanations

    drawing diagrams and shapes

    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
    0
    1.41
    9
    1.24
    لاً
    1.24
    ter
    1.21
    1
    1.17
    3
    1.12
    8
    1.07
    6
    1.05
    ि
    1.04
    spir
    1.02
    POSITIVE LOGITS
     দেখিল
    1.47
    wifery
    1.40
    蒡
    1.37
     ramifications
    1.37
     spacious
    1.35
     drawed
    1.32
     Regl
    1.32
     quench
    1.31
    mavros
    1.31
     supernatant
    1.30
    Activations Density 0.162%

    No Known Activations