© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9300
    Prev
    Next
    INDEX
    Explanations

    body, spear, constitution, identity, taller, task, number

    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
    Diethyl
    1.50
    淍
    1.49
    ேத்க
    1.46
    檛
    1.44
    Но
    1.41
    groupBy
    1.39
    들
    1.35
    sion
    1.34
    ‌లో
    1.33
    Cela
    1.32
    POSITIVE LOGITS
     mellitus
    1.24
    ן
    1.22
     sebuah
    1.20
    y
    1.16
    i
    1.07
    ので
    1.06
    rukh
    1.05
     willst
    1.04
     corp
    1.02
     outro
    1.01
    Activations Density 0.058%

    No Known Activations