© 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. 14298
    Prev
    Next
    INDEX
    Explanations

    Aurora with punctuation

    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
     công
    2.31
     acted
    1.96
     解
    1.90
     indicators
    1.88
    indicators
    1.84
     signif
    1.81
     enc
    1.77
     clashes
    1.76
     hallmarks
    1.76
    ʇ
    1.75
    POSITIVE LOGITS
    ة
    2.89
    mothers
    2.08
    orter
    2.06
    𝐀
    2.02
    loff
    2.02
    anzit
    1.99
    वंश
    1.87
    umption
    1.86
    جة
    1.85
     balancer
    1.85
    Activations Density 0.000%

    No Known Activations