© 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. 6563
    Prev
    Next
    INDEX
    Explanations

    equipped, available, designed, made

    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
     worse
    1.45
     clearest
    1.18
     better
    1.17
     faces
    1.15
     peor
    1.12
     mejores
    1.11
     fairer
    1.07
    癢
    1.05
     naming
    1.05
    Opens
    1.04
    POSITIVE LOGITS
    equipped
    1.89
    provided
    1.87
    オプション
    1.84
     voorzien
    1.82
    פשר
    1.82
    جمالي
    1.81
    装備
    1.76
    OPTIONS
    1.74
    PROVIDED
    1.73
    부분
    1.73
    Activations Density 0.212%

    No Known Activations