© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9927
    Prev
    Next
    INDEX
    Explanations

    4xx errors

    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_22_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
    多少
    1.17
    トレ
    1.08
    诉
    0.98
    illä
    0.96
     Seh
    0.91
     Bytes
    0.90
    ス
    0.89
     Brunner
    0.89
    UserModel
    0.88
    訟
    0.88
    POSITIVE LOGITS
     épa
    0.86
     avulla
    0.85
     jälkeen
    0.82
    odia
    0.79
     aikana
    0.77
     fundo
    0.77
     arrive
    0.76
    ૂર્વ
    0.74
     arasında
    0.74
     cheg
    0.73
    Activations Density 0.001%

    No Known Activations