© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    similarities and imports

    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
    ğı
    2.53
    WriteString
    2.35
    ೂರ್ವ
    2.28
    tní
    2.27
    είς
    2.24
    珑
    2.21
    lieu
    2.18
    𝘤
    2.15
    ınt
    2.12
    Offsets
    2.12
    POSITIVE LOGITS
    啉
    2.08
     flawless
    1.97
     ect
    1.95
     impeccable
    1.95
    ers
    1.91
     underlined
    1.83
     Eee
    1.82
    ্মান
    1.82
    儀
    1.79
    朵
    1.79
    Activations Density 0.000%

    No Known Activations