© 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. 11456
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
     mancanza
    2.67
    చిన
    2.64
    কালীন
    2.64
    ంబేద్కర్
    2.51
    தோ
    2.51
    𝒽
    2.50
    ත්මක
    2.47
     desactiv
    2.45
    सीएल
    2.45
    愫
    2.44
    POSITIVE LOGITS
    +}\
    2.40
    som
    2.37
    titleMargin
    2.37
     hel
    2.37
    headed
    2.36
    컹
    2.30
    scripts
    2.29
    utage
    2.27
    टरी
    2.27
    backer
    2.24
    Activations Density 0.018%

    No Known Activations