© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13125
    Prev
    Next
    INDEX
    Explanations

    `not` `have`

    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
     !
    1.98
    ુંદર
    1.96
    σιν
    1.95
    lax
    1.87
     Pamph
    1.86
    spl
    1.79
    ഗു
    1.78
     Such
    1.78
    ವ
    1.76
    णात
    1.76
    POSITIVE LOGITS
     ограничењима
    1.92
    ้น
    1.90
    enton
    1.77
     заре
    1.74
    タミン
    1.73
    জনকে
    1.72
    idler
    1.71
    encing
    1.68
    ल्पनिक
    1.68
    ahiye
    1.65
    Activations Density 0.000%

    No Known Activations