© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3069
    Prev
    Next
    INDEX
    Explanations

    `. It`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dims
    1.25
     Afric
    1.23
    ณ
    1.23
    左右
    1.20
     Quadro
    1.18
    名
    1.18
     namesake
    1.18
     oval
    1.16
    美
    1.15
     genera
    1.14
    POSITIVE LOGITS
     religieux
    1.32
     Trooper
    1.25
    ynet
    1.25
    搗
    1.24
    pliance
    1.19
    pray
    1.17
    obedience
    1.17
    olicy
    1.16
     kháng
    1.16
     králov
    1.15
    Activations Density 0.021%

    No Known Activations