© 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. 9233
    Prev
    Next
    INDEX
    Explanations

    attribute names and properties

    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
    1
    1.34
    0
    1.17
    3
    1.17
    5
    1.13
    6
    1.12
    7
    1.12
    8
    1.04
    4
    1.02
    9
    1.02
    2
    1.02
    POSITIVE LOGITS
     disability
    1.17
     ammunition
    1.13
     aids
    1.11
     relating
    1.10
    િજા
    1.09
     রহিল
    1.07
     muhimu
    1.06
     informatie
    1.06
     circumvent
    1.06
     لت
    1.06
    Activations Density 0.237%

    No Known Activations