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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 371
    Prev
    Next
    INDEX
    Explanations

    years starting with 20

    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
     mince
    0.87
    싫
    0.84
    اظ
    0.83
     helst
    0.80
    龋
    0.79
     auguri
    0.79
    CONDS
    0.77
    而成
    0.77
    HELLO
    0.77
     Algun
    0.76
    POSITIVE LOGITS
    nd
    1.66
    0
    1.41
     nd
    1.18
    nds
    1.03
    ND
    0.99
    nde
    0.96
    ০০০
    0.93
    ۰۰
    0.90
    ０
    0.84
    нда
    0.81
    Activations Density 0.804%

    No Known Activations