© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2172
    Prev
    Next
    INDEX
    Explanations

    you're experiencing these emotions

    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_17_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
    ierge
    0.80
     نوٹ
    0.80
    Zi
    0.74
     EMPTY
    0.73
     manned
    0.72
    ゼ
    0.72
     controlled
    0.71
    ĩ
    0.71
     Nota
    0.71
     continuous
    0.70
    POSITIVE LOGITS
     harm
    1.66
     justice
    1.45
    Justice
    1.44
     harms
    1.42
    justice
    1.41
     Justice
    1.31
     Harm
    1.30
     injustice
    1.29
     JUSTICE
    1.26
     injure
    1.25
    Activations Density 0.164%

    No Known Activations