© 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. 14200
    Prev
    Next
    INDEX
    Explanations

    Viktor Frankl and Chris Voss

    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
    府
    2.15
    梠
    2.02
    琶
    2.00
    ्राफी
    2.00
    域
    1.95
     alvo
    1.94
    面上
    1.93
    公園
    1.93
    ных
    1.89
    ත්මක
    1.89
    POSITIVE LOGITS
    irov
    1.75
    holding
    1.64
    TY
    1.63
    น้อง
    1.62
    SCH
    1.62
    ا
    1.59
    koľ
    1.58
     yandan
    1.55
    ty
    1.54
    꿩
    1.54
    Activations Density 0.021%

    No Known Activations