© 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. 74
    Prev
    Next
    INDEX
    Explanations

    absence of things

    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
     впечат
    0.89
    Primer
    0.88
     spannend
    0.88
    +{\
    0.87
    ドキ
    0.85
     विराज
    0.84
    講解
    0.84
    interpr
    0.82
    WebContent
    0.81
    andaş
    0.81
    POSITIVE LOGITS
     disappearance
    2.99
     disappear
    2.94
     removal
    2.83
    消失
    2.81
     disappearing
    2.77
     removed
    2.74
    退出
    2.73
     disappeared
    2.73
     discontinuation
    2.72
    撤
    2.66
    Activations Density 6.561%

    No Known Activations