© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 3269
    Prev
    Next
    INDEX
    Explanations

    company, local, animation, years, json

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    7
    1.52
    8
    1.35
     Aluminum
    1.32
    ٧
    1.31
    aluminum
    1.25
     neutroph
    1.24
     десятки
    1.24
     lightness
    1.23
     cesium
    1.22
    ۷
    1.20
    POSITIVE LOGITS
    istry
    1.51
     either
    1.46
    isted
    1.42
     scheme
    1.41
     organisation
    1.40
     policy
    1.38
    istration
    1.35
    際には
    1.33
    edia
    1.32
     both
    1.29
    Activations Density 0.025%

    No Known Activations