© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    nn.Module class definitions

    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
    მწიფ
    2.90
     суток
    2.81
    ଟ
    2.77
    ═
    2.74
    arendon
    2.72
    䐝
    2.69
    ଁ
    2.67
    𒉺
    2.66
    phants
    2.64
    ीय
    2.63
    POSITIVE LOGITS
    彻
    2.05
    X
    2.03
     ra
    1.98
     invalidate
    1.95
    हायला
    1.93
     into
    1.92
     komme
    1.92
     تكبرها
    1.91
     advant
    1.90
    heap
    1.88
    Activations Density 0.035%

    No Known Activations