© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14393
    Prev
    Next
    INDEX
    Explanations

    principles of

    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
    នុ
    1.77
    моби
    1.76
    کنندگان
    1.72
    ក្ខ
    1.71
    θη
    1.61
    舶
    1.58
     Після
    1.57
    ្សែ
    1.56
     Adası
    1.54
    aży
    1.54
    POSITIVE LOGITS
    。
    1.85
     het
    1.59
     the
    1.59
     vetor
    1.58
     width
    1.44
     df
    1.43
    .
    1.42
     i
    1.40
     paris
    1.39
    。.
    1.37
    Activations Density 0.071%

    No Known Activations