© 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. 53-GEMMASCOPE-2-RES-65K
    7. 5570
    Prev
    Next
    INDEX
    Explanations

    words connecting clauses

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

    am programmed to refuse

    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_53_width_65k_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
    px
    0.41
    rod
    0.38
     orij
    0.37
    ogy
    0.37
    ^{\
    0.37
    elesaian
    0.36
     xo
    0.36
     usage
    0.36
    leans
    0.36
    rici
    0.36
    POSITIVE LOGITS
    ADB
    0.41
    ̣
    0.41
    '$.
    0.41
    PMS
    0.40
    linalg
    0.39
     Δε
    0.39
    ‖</
    0.39
    AUDIO
    0.39
    fact
    0.39
     Επι
    0.38
    Activations Density 0.034%

    No Known Activations