© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    holding onto something

    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
     cut
    2.09
     wo
    2.07
     near
    2.04
     volto
    1.99
    토
    1.95
    ting
    1.95
     re
    1.89
     செய்து
    1.85
     NEAR
    1.78
    ↵
    1.76
    POSITIVE LOGITS
    かけた
    2.95
    weathermap
    2.83
    𝙞
    2.68
    ુક
    2.64
     组件
    2.62
     kald
    2.56
    リエステル
    2.55
    oscopes
    2.53
    acionais
    2.53
     rama
    2.52
    Activations Density 0.081%

    No Known Activations