© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14225
    Prev
    Next
    INDEX
    Explanations

    herpes, tape, or retrograde

    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
    تي
    2.56
    
    2.33
    ديد
    2.30
    antz
    2.29
    𝘳
    2.26
    ಮುಖ
    2.22
    ้าว
    2.21
    ​
    2.19
    dus
    2.16
    ted
    2.14
    POSITIVE LOGITS
    ா
    3.03
    اا
    2.96
    Tape
    2.92
    ेर
    2.85
    ا۔
    2.84
    ا
    2.81
    ិច
    2.80
     kuma
    2.73
    榞
    2.73
     Tape
    2.71
    Activations Density 0.004%

    No Known Activations