© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10527
    Prev
    Next
    INDEX
    Explanations

    programming, electronics, AI, Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     高
    1.89
     영국
    1.79
     세계
    1.77
     네트워크
    1.68
    autumn
    1.68
     그러나
    1.67
     어린이
    1.66
     유럽
    1.66
     特
    1.65
     autumn
    1.64
    POSITIVE LOGITS
     nesse
    1.56
     solamente
    1.55
     desse
    1.51
     iniciando
    1.47
     inicia
    1.44
     termino
    1.43
     ocasion
    1.42
     referente
    1.37
     nessa
    1.36
     mencion
    1.35
    Activations Density 0.026%

    No Known Activations