© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11597
    Prev
    Next
    INDEX
    Explanations

    smaller than its square root

    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_7_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
    tope
    1.71
    Scissors
    1.65
    ❼
    1.64
    Nissan
    1.64
    खास्त
    1.61
    𝐾
    1.59
     সীমান্তের
    1.58
    commons
    1.56
    FilesIn
    1.56
     velocidade
    1.55
    POSITIVE LOGITS
     ac
    1.25
     or
    1.23
     ca
    1.21
     associated
    1.18
     born
    1.18
     aj
    1.17
     من
    1.15
     c
    1.13
     former
    1.10
     wrong
    1.09
    Activations Density 0.366%

    No Known Activations