© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6401
    Prev
    Next
    INDEX
    Explanations

    building quality connections

    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
     Gauss
    1.27
     mouseY
    1.24
    leich
    1.22
    ével
    1.20
    өк
    1.19
    asso
    1.16
    챗
    1.16
    OGA
    1.12
    ungle
    1.10
    elig
    1.09
    POSITIVE LOGITS
    築
    2.01
    building
    1.81
     dibangun
    1.71
     blossoms
    1.68
     reconstru
    1.59
     rebuilding
    1.57
     building
    1.52
     builder
    1.51
     blossom
    1.51
    BUILD
    1.51
    Activations Density 0.099%

    No Known Activations