© 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. 14244
    Prev
    Next
    INDEX
    Explanations

    HTML headings

    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
     gyd
    2.14
     affective
    1.90
     employed
    1.81
     aesthetically
    1.80
     allant
    1.78
     LOW
    1.78
     divorced
    1.74
     극
    1.74
     வைத்திய
    1.74
     low
    1.69
    POSITIVE LOGITS
    aterial
    1.71
    ã
    1.62
    enee
    1.60
     Detail
    1.59
    ãos
    1.56
    anning
    1.54
    anh
    1.54
    ître
    1.53
    ले
    1.53
    eryllium
    1.52
    Activations Density 0.014%

    No Known Activations