© 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. 5750
    Prev
    Next
    INDEX
    Explanations

    ground-penetrating radar, risk, lord, ears, water, hospital, pacific, start

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

    upward movement and improvement

    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
    increased
    0.43
    -'
    0.41
    probable
    0.40
    circum
    0.39
    elapsed
    0.39
    permitted
    0.38
    biggest
    0.38
    -‘
    0.38
    irregular
    0.37
    -"
    0.36
    POSITIVE LOGITS
    Based
    0.37
    Ahead
    0.35
    In
    0.35
    Up
    0.34
    Off
    0.33
    Builder
    0.33
    Scoped
    0.33
    E
    0.33
    Speak
    0.32
    Ease
    0.32
    Activations Density 0.104%

    No Known Activations