© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11553
    Prev
    Next
    INDEX
    Explanations

    speaking out freely

    np_acts-logits-general · gemini-2.5-flash-lite

    suppression of dissent and judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    Batt
    0.43
    opedic
    0.37
    π
    0.37
    batt
    0.37
    椥
    0.36
    IsPass
    0.36
     სან
    0.36
     सद्
    0.35
     Manipulation
    0.35
    自信
    0.35
    POSITIVE LOGITS
     inconvenient
    1.13
     dissent
    1.00
     dissenting
    0.92
     perceived
    0.90
     pesky
    0.85
     unwelcome
    0.84
    忤
    0.84
     inconvenience
    0.81
     slightest
    0.80
     undesired
    0.79
    Activations Density 0.408%

    No Known Activations