© 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. 10927
    Prev
    Next
    INDEX
    Explanations

    modern slang

    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
    หม
    1.88
     blame
    1.81
     neglig
    1.66
    ์
    1.66
     incon
    1.57
     uneven
    1.57
    ed
    1.56
     опреде
    1.51
    ుల
    1.51
    компа
    1.50
    POSITIVE LOGITS
    나라
    2.28
    山市
    2.16
    NLP
    2.10
    bungen
    2.02
     Texte
    2.01
    ribusiness
    1.95
    潟
    1.94
     뜻
    1.89
     Sprachen
    1.89
     "`
    1.89
    Activations Density 0.019%

    No Known Activations