© 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. 3007
    Prev
    Next
    INDEX
    Explanations

    situation and its context

    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
    unda
    2.23
     dor
    2.11
    ahoo
    2.09
    })$.
    2.07
     حوال
    2.03
    idding
    1.99
    MDEwOlJlcG
    1.97
    idded
    1.93
    рет
    1.92
    দ্ভুত
    1.91
    POSITIVE LOGITS
    复制代码
    3.50
    կ
    2.96
    互联网档案馆
    2.93
    LEncoder
    2.89
    ױ
    2.88
    जानिए
    2.88
    \]
    2.86
    𒁳
    2.81
     deviceInfo
    2.80
    MSBuildTools
    2.75
    Activations Density 0.291%

    No Known Activations